product-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The 'Auto-draft from codebase' feature in Step 2 of the workflow ingests data from external, potentially untrusted sources within the repository. Malicious instructions placed in these files by an attacker could influence the agent's output or behavior during the drafting process.\n
- Ingestion points: SKILL.md specifies reading repository files including README, landing pages, marketing copy, about pages, meta descriptions, and package.json.\n
- Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded commands within the ingested files.\n
- Capability inventory: The skill is capable of reading various project files and writing the resulting context to
.agents/product-marketing.md.\n - Sanitization: No explicit sanitization, escaping, or validation of the content read from the codebase is implemented before it is interpolated into the drafting prompt.
Audit Metadata