x-bookmark-quote-posts

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) because it ingests untrusted text data from the external X/Twitter platform.
  • Ingestion points: Data is fetched from X/Twitter bookmarks and user profile timelines via the in-app browser.
  • Boundary markers: The instructions do not specify the use of clear delimiters or instructions for the agent to ignore command-like text embedded within the retrieved social media posts.
  • Capability inventory: The skill is authorized to perform filesystem writes, browser navigation, and Git operations (git status, git commit, git diff).
  • Sanitization: There is no explicit logic described to sanitize or filter the content retrieved from the web before it is processed by the language model.
  • [COMMAND_EXECUTION]: The skill performs shell command execution through Git utilities to manage the generated quote-post drafts. Specifically, it uses git status --short, git diff --check, and git commit to maintain the repository state and version the output files in data/x-growth/bookmark-quote-posts/.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 01:37 PM
Security Audit — agent-trust-hub — x-bookmark-quote-posts