61-budget-planning
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data which could potentially contain malicious instructions.
- Ingestion points: The skill instructions in
SKILL.mddirect the agent to read from.agents/product-marketing-context.md, external marketing plans, and previous performance reports. - Boundary markers: The skill does not instruct the agent to use specific delimiters or to ignore instructions embedded within the ingested text files.
- Capability inventory: The skill is limited to generating markdown reports and does not utilize high-risk capabilities such as network requests, subprocess execution, or arbitrary file system writes.
- Sanitization: No sanitization or validation methods are specified for the external data being processed.
Audit Metadata