community-health-monitoring
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from X (Twitter) profiles and tweets, creating a surface for indirect prompt injection attacks.\n
- Ingestion points: Follower profiles via
x_get_followers(bios and metadata) and tweet content viax_get_tweetsas detailed inSKILL.md.\n - Boundary markers: Absent. The workflow lacks explicit delimiters or instructions to ignore commands within the fetched profile data.\n
- Capability inventory: The skill utilizes scripts such as
src/blockBots.jsandsrc/unfollowback.jswhich perform automated write operations on the user's account based on the results of the analysis.\n - Sanitization: Absent. No content filtering or validation mechanisms are described for the fetched social media data before it is processed by the agent.
Audit Metadata