popup-cro
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read an external file for context, which could potentially contain malicious instructions that influence the agent's behavior.
- Ingestion points: Reads
.claude/product-marketing-context.mdif it exists (SKILL.md). - Boundary markers: None identified in the prompt instructions to distinguish between data and instructions within the context file.
- Capability inventory: The skill itself does not appear to have risky capabilities like network access, file writing, or command execution.
- Sanitization: There are no explicit instructions for the agent to sanitize or ignore embedded commands within the ingested file.
Audit Metadata