ciso-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, which presents a surface for indirect prompt injection if those sources contain adversarial instructions.
- Ingestion points: The agent is explicitly instructed to read
company-context.mdbefore responding and can receive data from other agent roles through the[INVOKE]mechanism. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the content read from the external context or role invocations.
- Capability inventory: The skill possesses the capability to write to the local file system using the provided Python scripts (
risk_quantifier.pyandcompliance_tracker.py), which export analysis results to CSV and JSON files. - Sanitization: The included scripts process inputs into structured formats but do not implement specific security sanitization or validation logic to detect or neutralize malicious payloads within the ingested data.
Audit Metadata