competitors
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local context files to inform the creation of competitor comparison pages.
- Ingestion points: The skill explicitly instructs the agent in SKILL.md to read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md before proceeding with page generation.
- Boundary markers: None identified. The skill does not implement specific delimiters or instructions to ignore instructions embedded within the ingested context files.
- Capability inventory: The skill is restricted to generating text copy, YAML metadata, and content structure for marketing pages; it does not execute shell commands or perform network operations within its own logic.
- Sanitization: None identified. The content from the context files is used directly to inform the agent's output without explicit validation or filtering logic.
Audit Metadata