tracing-knowledge-lineages
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell-based git commands, such as
git log,git blame, andgit show, to retrieve historical context from the repository source and metadata. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the project's history, creating an indirect prompt injection surface.
- Ingestion points: Historical git logs, commit messages, PR discussions, and documents within the
docs/anddocs/adr/directories. - Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the processed historical data.
- Capability inventory: Access to shell execution for git archaeology tasks.
- Sanitization: No sanitization or validation of the ingested historical text is specified in the workflow.
Audit Metadata