check-traceability
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local repository scripts
.guardrails/scripts/check-trace.shand.guardrails/scripts/check-ids.shto perform documentation audits. - [INDIRECT_PROMPT_INJECTION]: The agent is instructed to read and interpret various documentation artifacts (SRS, RMF, SAD, SOUP, problems) to guide fixes, representing an untrusted data ingestion surface.
- Ingestion points: Documentation artifacts (SRS, RMF, SAD, SOUP, problem reports) and the
.guardrails/config.yamlfile. - Boundary markers: The skill does not provide instructions for using delimiters or boundary markers to isolate data from instructions when reading artifacts.
- Capability inventory: The agent can execute shell commands and modify local files based on interpreted content.
- Sanitization: No explicit sanitization or validation of the content of the artifacts is performed by the agent before processing.
Audit Metadata