x-bookmark-quote-posts

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill accesses https://x.com/i/bookmarks to collect the user's latest bookmarked posts. This is a legitimate network operation targeting a well-known service as part of the skill's primary functionality.
  • [COMMAND_EXECUTION]: Utilizes local git commands (status, diff, commit) to manage content drafts within the user's workspace repository. These operations are restricted to the task of maintaining the quote-post queue.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external X/Twitter posts.
  • Ingestion points: Fetches post text and metadata from https://x.com/i/bookmarks (SKILL.md).
  • Boundary markers: None identified; there are no delimiters or instructions to ignore embedded prompts in the ingested data.
  • Capability inventory: The agent can write markdown files to the local filesystem and perform git commit operations (SKILL.md).
  • Sanitization: No specific sanitization or filtering logic is defined for the external bookmark content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 01:59 PM
Security Audit — agent-trust-hub — x-bookmark-quote-posts