paywall-upgrade-cro
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read a local file ('.agents/product-marketing-context.md' or '.claude/product-marketing-context.md') to gain product context before responding. This creates an indirect prompt injection surface where malicious instructions could be embedded in the context file.
- Ingestion point: SKILL.md (Initial Assessment section).
- Boundary markers: None present to distinguish context data from agent instructions.
- Capability inventory: The skill is primarily instructional for generating marketing advice and does not explicitly request dangerous tools or perform network/file system writes.
- Sanitization: No sanitization or validation of the external context file content is described.
Audit Metadata