omh-feedback-triage
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted customer signals and feedback items, which may contain embedded instructions intended to override agent behavior.\n
- Ingestion points: External feedback items and summaries are processed directly within the triage workflow (SKILL.md).\n
- Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious prompts within the input data, though it references identifying a 'source boundary'.\n
- Capability inventory: The skill documentation does not list access to dangerous capabilities such as arbitrary subprocess execution, file system modifications, or network-based exfiltration tools.\n
- Sanitization: The skill contains explicit safety instructions to ensure that names, emails, order IDs, and credit card digits are masked in the processed output.
Audit Metadata