hai-razor
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze a wide variety of project-related data, including PRDs, documentation, code, and logs, which could contain malicious instructions designed to manipulate the agent's reasoning or the resulting audit report.
- Ingestion points: SKILL.md (Step 2) identifies PRDs, docs, code, schemas, traces, tests, metrics, user flows, support cases, and decision records as input sources.
- Boundary markers: The instructions do not define boundary markers or include warnings to ignore instructions embedded within the analyzed data.
- Capability inventory: The skill performs file read operations on the input sources and generates an HTML report on the local file system at
/tmp/hai-razor-<slug>/index.html. - Sanitization: There is no mention of sanitizing, escaping, or filtering the ingested content before it is processed by the agent.
Audit Metadata