pricing
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest content from local files such as
.agents/product-marketing.mdto inform its pricing recommendations. This establishes an ingestion point for untrusted data that could contain malicious instructions. However, the skill lacks any scripts or tools with executable capabilities, mitigating the potential for high-impact exploitation. - Ingestion points:
SKILL.md(accesses.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.md). - Boundary markers: Absent; the skill does not specify delimiters or provide instructions to ignore embedded commands.
- Capability inventory: None; there are no shell scripts, Python/Node.js code, or tool definitions within the skill files.
- Sanitization: Absent; no validation or escaping is applied to the ingested marketing context data.
Audit Metadata