compliance-checker
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied content such as social posts, blog articles, and landing pages. This creates a potential surface where malicious instructions embedded in the input content could attempt to influence the agent's behavior.
- Ingestion points: The
contentparameter in theSKILL.mdinput schema accepts arbitrary text, markdown, or HTML from the user for analysis. - Boundary markers: The skill does not provide specific instructions or delimiters to distinguish between analyzed data and its own task instructions, increasing the risk of instruction confusion.
- Capability inventory: The skill is restricted to reading specific local documentation files (
shared/references/ftc-compliance.md) and generating textual reports. It lacks access to network tools, shell execution, or persistent file storage. - Sanitization: There is no evidence of input validation or sanitization of the provided content before it is processed by the agent.
Audit Metadata