oma-docs
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository documentation and git diffs. This creates a potential surface where malicious instructions embedded in these files could theoretically influence the agent's actions during the documentation sync or verification process.
- Ingestion points: Processes arbitrary markdown files and git diff outputs specified in target paths.
- Boundary markers: Relies on an external execution-policy.md; no internal delimiters are specified for untrusted document content in the skill instructions.
- Capability inventory: Capability to propose and apply filesystem patches via git and the OMA CLI.
- Sanitization: Includes guardrails to specifically exclude secret-bearing files (.env, private keys) and requires verification of patches against current code context.- [EXTERNAL_DOWNLOADS]: Mentions the use of lychee for URL verification, which is a well-known utility commonly installed via standard package managers.- [COMMAND_EXECUTION]: Utilizes the oma docs CLI and git to perform documentation verification and synchronization tasks as part of its core functionality.
Audit Metadata