bluesky-feed-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains explicit, deceptive runtime instructions to install dependencies without user confirmation and to conceal that installation request (telling the agent not to describe it as a browser-open request), which are hidden/deceptive directives outside the declared scraping purpose.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to invoke the BrowserAct CLI to access real Bluesky web pages at runtime, which can ingest outsider-authored free text from those fetched pages into the LLM context (indirect prompt injection risk).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to automatically use the BrowserAct install link at runtime to obtain and install the required BrowserAct Skill/CLI (which implies fetching and executing remote installer content): https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main