repo-docs-align
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The helper script
scripts/new_repo_docs_align_artifact.pyinvokessubprocess.runto callgit check-ignore. This call uses a parameterized list of arguments and disables shell execution (shell=False), ensuring no risk of shell command injection. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process documentation surfaces and source code comments across a repository, creating a potential attack surface for indirect prompt injection if external or untrusted repository contents are analyzed.
- Ingestion points: Reads repository files such as
AGENTS.md,README.md, specs, runbooks, and localized code comments during drift analysis. - Boundary markers: Absent; there are no explicit prompt delimiters or containment instructions defined to separate file content from the agent's instructions.
- Capability inventory: Modifies local repository files, creates workspace directories under
.agents/, appends ignore rules to.gitignore, and spawns read-only explorer subagents. - Sanitization: Does not explicitly sanitize or filter incoming text from the repository files before processing it for documentation synchronization.
Audit Metadata