blocking-muting-management
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from X (Twitter) including follower bios, usernames, and tweet text for bot detection and keyword-based muting actions.
- Ingestion points: External data from follower profiles and timeline content are ingested by scripts like src/blockBots.js and src/muteByKeywords.js.
- Boundary markers: There are no specified boundary markers or instructions to the agent to ignore embedded commands within the ingested data.
- Capability inventory: The skill allows the agent to perform authenticated write operations on the user's account, such as mass blocking, muting, and reporting accounts.
- Sanitization: The documentation does not describe any sanitization or validation of external strings before they are evaluated against heuristics or keyword lists.
- [COMMAND_EXECUTION]: The skill relies on a manual "Self-XSS" pattern, instructing users to paste JavaScript code from the src/ directory into the browser DevTools console. While this is a common method for browser automation tools, it bypasses standard security boundaries and requires the user to manually verify the script's safety.
Audit Metadata