owasp-top-10-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external repository data including code, configurations, dependency manifests, and documentation. This creates an attack surface for indirect prompt injection, where malicious instructions embedded in the analyzed repository files could potentially influence the agent's behavior during the assessment.
- Ingestion points: The skill instructs the agent to "check relevant code, configuration, dependency manifests, build settings, and runtime hardening" from a target repository.
- Boundary markers: The instructions do not specify the use of delimiters or provide explicit warnings for the agent to ignore instructions contained within the data being analyzed.
- Capability inventory: The skill involves reading files and performing information gathering to identify sensitive assets and attack surfaces.
- Sanitization: There is no mention of sanitizing or validating the content ingested from the external repository.
Audit Metadata