canonical-docs
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to verify behavior by running "documented operations" (e.g., configuration, migration, and recovery instructions). This creates a surface for indirect prompt injection if the documentation being processed contains malicious commands.
- Ingestion points: Processes external engineering documentation and implementation code.
- Boundary markers: No specific delimiters or warnings for embedded instructions are provided.
- Capability inventory: Encourages the execution of shell commands/operations found in external documentation.
- Sanitization: No input validation or sanitization of documentation content before execution is mentioned.
Audit Metadata