source-driven-development
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface where external documentation pages are processed. It implements defensive boundary markers by instructing the agent to treat fetched content as data and ignore directives like 'ignore previous instructions'.
- [DATA_EXFILTRATION]: The instructions mitigate data exfiltration risks by advising the agent against automatically hardcoding telemetry or analytics endpoints found in documentation examples into the generated output.
Audit Metadata