retail-media
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 and apply context from local files including
.agents/marketing-learnings.mdand.agents/marketing-strategy.md. This represents an indirect prompt injection surface where data previously written to these files (e.g., from prior interactions or external data sources) could influence the agent's behavior in the current session. - Ingestion points: Files
.agents/marketing-learnings.mdand.agents/marketing-strategy.md(referenced in SKILL.md). - Boundary markers: None provided in the instructions to delimit external data from system instructions.
- Capability inventory: The skill primarily provides planning and advisory functions; no dangerous tools (like shell execution or network writing) are explicitly invoked within these instructions.
- Sanitization: There are no instructions for the agent to sanitize or ignore potential commands embedded within these files.
Audit Metadata