documentation
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: No malicious code, prompt injection, or data exfiltration patterns were detected. The skill is focused exclusively on documentation standards and factual verification.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection as it involves processing existing documentation and source code to generate updates.\n
- Ingestion points: Ingests existing user and developer documentation and source code to identify requirements and current behavior (SKILL.md).\n
- Boundary markers: Absent; the instructions do not provide specific delimiters or warnings for the agent to ignore instructions embedded in the ingested data.\n
- Capability inventory: Modifying and updating documentation files within the repository (SKILL.md).\n
- Sanitization: Absent; there are no explicit requirements for sanitizing or escaping the data read from external sources.\n
- Assessment: This surface is inherent to documentation tasks and is mitigated by the skill's explicit focus on truthfulness and verification against observed operation.\n- [EXTERNAL_DOWNLOADS]: The skill references the
okf-authoringtool maintained in thenrkno/okf-mcprepository for managing document metadata and indexing. This is a reference to established tooling from a well-known organization (NRK) and does not involve risky automated execution or unverified remote code.
Audit Metadata