x-bookmark-quote-posts
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external source (https://x.com/i/bookmarks) to generate content drafts.
- Ingestion points: Content is collected from X bookmarks using the Codex in-app browser as described in SKILL.md.
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded prompts within the bookmarked text.
- Capability inventory: The skill can write files to the local file system (data/x-growth/bookmark-quote-posts/) and execute git commands (git status, git diff, git commit).
- Sanitization: There is no evidence of sanitization or filtering of the external bookmark content before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill uses Git commands to manage the generated content drafts.
- The instructions include executing 'git status --short', 'git diff --check', and 'git commit'.
- These operations are limited to the content repository context and are consistent with the skill's stated purpose of maintaining a quote-post queue.
Audit Metadata