run-organic-social-post-check
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of draft social media posts and external 'public sources' used for fact-checking world facts and category education.
- Ingestion points: Untrusted data enters the agent's context through user-provided drafts and external web sources retrieved during the claims verification process described in
SKILL.md(Step 4). - Boundary markers: The instructions do not specify any delimiters or safety warnings to prevent the agent from obeying instructions embedded within the social media drafts or retrieved web content.
- Capability inventory: The skill has the capability to rewrite content, make decisions on brand safety, and interacts with long-term memory skills such as
save-learningandsave-to-brain(referenced inskill.meta.json). - Sanitization: There is no evidence of sanitization, escaping, or structural validation of the external content before it is used to influence the agent's outputs or its learned memory.
Audit Metadata