skills/seaworld008/commonly-used-high-value-skills/information-security-manager-iso27001/Gen Agent Trust Hub
information-security-manager-iso27001
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied CSV files for assets and compliance status, creating a potential surface for indirect prompt injection attacks where malicious data could influence agent behavior.
- Ingestion points: The scripts
scripts/risk_assessment.pyandscripts/compliance_checker.pyaccept external data via the--assetsand--controls-filecommand-line arguments. - Boundary markers: The instructions do not define clear delimiters or provide specific warnings for the agent to treat input data as untrusted text rather than instructions.
- Capability inventory: The skill includes Python scripts capable of writing files to the local filesystem using the
--outputparameter. - Sanitization: The provided scripts parse standard CSV format and interpolate field values directly into reports (JSON, CSV, Markdown) without validating or escaping content for prompt injection patterns.
Audit Metadata