mentionedon-answer-capture
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill instructs the agent to send user-supplied observations to an external API endpoint at
https://mentioned-on.com/mcp. While this is the intended purpose of the skill (using thesummarize_scan_evidencetool), it involves transmitting potentially sensitive user-provided AI captures to a non-whitelisted third-party domain. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of AI-generated answer captures supplied by the user.
- Ingestion points: User-provided text captures of AI assistant responses (found in
SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore embedded instructions within the user-supplied content.
- Capability inventory: The skill has the capability to perform network operations by sending data to the
mentioned-on.comendpoint. - Sanitization: There are no explicit instructions for sanitizing or escaping the external content before it is processed or sent to the external tool.
Audit Metadata