x-bookmark-quote-posts
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external social media profiles, creating a surface for indirect prompt injection where adversarial content could influence agent behavior.
- Ingestion points: The skill reads authored posts and bookmark feeds from X.com via an in-app browser (SKILL.md, lines 35-43 and 62-71).
- Boundary markers: There are no explicit instructions or delimiters provided to ensure the agent ignores or isolates potential instructions embedded within the fetched X posts.
- Capability inventory: The agent is authorized to write to local files (
data/x-growth/bookmark-quote-posts/) and execute git commands (status,diff,commit). - Sanitization: No sanitization, filtering, or validation steps are defined to process the external text before it is drafted into files or committed to the repository.
- [COMMAND_EXECUTION]: The skill utilizes shell commands to manage the state of the content repository.
- Evidence: The workflow includes calls to
git status --short,git diff --check, andgit commit -m "..."to track and save generated drafts (SKILL.md, lines 17, 106, 110).
Audit Metadata