tweetsmash-api
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves bookmarked posts from the TweetSmash API, which contains untrusted user-generated content (tweets).
- Ingestion points: The
GET /bookmarksendpoint, documented inreferences/api-reference.md, fetches tweet text and metadata into the agent's context. - Boundary markers: The skill lacks explicit delimiters or instructions in
SKILL.mdto ignore potential instructions embedded within the retrieved tweet content. - Capability inventory: The skill's capabilities are restricted to REST API interactions via
curland the execution of a local Python helper script; it does not provide a path for the untrusted content to be executed as code or shell commands. - Sanitization: No sanitization, validation, or filtering of the API-provided content is performed before processing.
Audit Metadata