brand-voice
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from social media posts, which could contain instructions designed to influence the agent's behavior.
- Ingestion points: The
list_posts_advancedtool (Step 1 inSKILL.md) retrieves up to 50 published posts. - Boundary markers: No specific delimiters or 'ignore instructions' warnings are defined for the post content analysis.
- Capability inventory: The skill is primarily focused on text analysis and generation based on the retrieved data.
- Sanitization: There is no evidence of sanitization or filtering to prevent the agent from obeying instructions found within the posts.
Audit Metadata