🐦 Twitter Post Details

Viewing enriched Twitter post

@akshay_pachaar

NVIDIA might just have open-sourced one of the most important AI projects right now. everyone is building skills, and we are also pulling in skills other people wrote and downloading them straight off GitHub. the skill is not just text. it bundles instructions and real executable code, and your agent runs that code with the same access you have. so a skill you grabbed to save ten minutes can read your environment variables, lift your API keys, and quietly send them somewhere. recent research found roughly 1 in 4 public skills carry a vulnerability, and a smaller slice are outright malicious. that is the gap SkillSpector closes. it is a security scanner that answers one question before you install anything: is this skill safe to run. you point it at a skill, and a local folder, a single skill .md file, a GitHub link, or a zip all work. it then runs two passes over the code. a fast static pass flags risky patterns like credential harvesting, data leaks, and prompt injection, and checks the dependencies against live cve data. an optional second pass uses an LLM to read intent and clear out false positives. at the end you get one risk score from 0 to 100 and a plain verdict that reads as safe, caution, or do not install. it is open source under Apache 2.0 and scans skills for Claude Code, Codex CLI, and Gemini. worth a run before you trust the next skill you find online. link to the GitHub repo: https://t.co/iaPlOvQ3t4

Media 1
Media 2

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2065412599001625058/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2065412599001625058/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2065412599001625058/media_1.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2065412599001625058/media_1.jpg",
      "type": "photo",
      "filename": "media_1.jpg"
    }
  ],
  "processed_at": "2026-06-13T05:04:09.833438",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2065412599001625058",
  "url": "https://x.com/akshay_pachaar/status/2065412599001625058",
  "twitterUrl": "https://twitter.com/akshay_pachaar/status/2065412599001625058",
  "text": "NVIDIA might just have open-sourced one of the most important AI projects right now.\n\neveryone is building skills, and we are also pulling in skills other people wrote and downloading them straight off GitHub.\n\nthe skill is not just text. it bundles instructions and real executable code, and your agent runs that code with the same access you have.\n\nso a skill you grabbed to save ten minutes can read your environment variables, lift your API keys, and quietly send them somewhere. recent research found roughly 1 in 4 public skills carry a vulnerability, and a smaller slice are outright malicious.\n\nthat is the gap SkillSpector closes. it is a security scanner that answers one question before you install anything: is this skill safe to run.\n\nyou point it at a skill, and a local folder, a single skill .md file, a GitHub link, or a zip all work.\n\nit then runs two passes over the code. a fast static pass flags risky patterns like credential harvesting, data leaks, and prompt injection, and checks the dependencies against live cve data.\n\nan optional second pass uses an LLM to read intent and clear out false positives.\n\nat the end you get one risk score from 0 to 100 and a plain verdict that reads as safe, caution, or do not install.\n\nit is open source under Apache 2.0 and scans skills for Claude Code, Codex CLI, and Gemini.\n\nworth a run before you trust the next skill you find online.\n\nlink to the GitHub repo: https://t.co/iaPlOvQ3t4",
  "source": "Twitter for iPhone",
  "retweetCount": 104,
  "replyCount": 35,
  "likeCount": 792,
  "quoteCount": 9,
  "viewCount": 54820,
  "createdAt": "Fri Jun 12 12:35:11 +0000 2026",
  "lang": "en",
  "bookmarkCount": 1187,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2065412599001625058",
  "displayTextRange": [
    0,
    271
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "akshay_pachaar",
    "url": "https://x.com/akshay_pachaar",
    "twitterUrl": "https://twitter.com/akshay_pachaar",
    "id": "703601972",
    "name": "Akshay 🚀",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1578327351544360960/YFpWSWIX_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/703601972/1733646485",
    "description": "",
    "location": "Learn AI Engineering 👉",
    "followers": 276702,
    "following": 490,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Wed Jul 18 18:58:39 +0000 2012",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 22668,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 5146,
    "statusesCount": 21129,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "1724322731376918560"
    ],
    "profile_bio": {
      "description": "Simplifying LLMs, AI Agents, RAG, and Machine Learning for you! • Co-founder @dailydoseofds_• BITS Pilani • 3 Patents • ex-AI Engineer @ LightningAI",
      "entities": {
        "description": {
          "user_mentions": [
            {
              "id_str": "",
              "indices": [
                77,
                92
              ],
              "name": "",
              "screen_name": "dailydoseofds_"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "join.dailydoseofds.com",
              "expanded_url": "http://join.dailydoseofds.com",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/TLsKA1eQsf"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/nSsBnWc5bg",
        "expanded_url": "https://twitter.com/akshay_pachaar/status/2065412599001625058/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2065412168674365440",
        "indices": [
          272,
          295
        ],
        "media_key": "3_2065412168674365440",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARyp0WykmtAACgACHKnR0NYbseIAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHKnRbKSa0AAKAAIcqdHQ1hux4gAA",
            "media_key": "3_2065412168674365440"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HKnRbKSa0AAzL1d.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 690,
              "w": 1232,
              "x": 0,
              "y": 0
            },
            {
              "h": 1232,
              "w": 1232,
              "x": 0,
              "y": 0
            },
            {
              "h": 1404,
              "w": 1232,
              "x": 0,
              "y": 0
            },
            {
              "h": 1420,
              "w": 710,
              "x": 318,
              "y": 0
            },
            {
              "h": 1420,
              "w": 1232,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1420,
          "width": 1232
        },
        "sizes": {
          "large": {
            "h": 1420,
            "w": 1232
          }
        },
        "type": "photo",
        "url": "https://t.co/nSsBnWc5bg"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "github.com/NVIDIA/SkillSp…",
        "expanded_url": "https://github.com/NVIDIA/SkillSpector",
        "indices": [
          1426,
          1449
        ],
        "url": "https://t.co/iaPlOvQ3t4"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}