competitor-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an ingestion point for potentially untrusted data by instructing the agent to read 'app-marketing-context.md' for context.
- Ingestion points: 'app-marketing-context.md' (referenced in SKILL.md).
- Boundary markers: Absent; there are no instructions provided to separate the ingested file content from the agent's operational logic.
- Capability inventory: The skill operates using the agent's default platform capabilities, including file access and search.
- Sanitization: Absent; the skill does not define any validation or filtering requirements for the context file being read.
Audit Metadata