understand-diff
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from local sources which could theoretically contain malicious instructions.
- Ingestion points: Processes output from
git diffand reads the content of.understand-anything/knowledge-graph.json. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when processing the data.
- Capability inventory: The skill can execute shell commands (
git,grep) and write to specific local files (.understand-anything/diff-overlay.json). - Sanitization: No explicit sanitization or filtering of the ingested content is mentioned.
- [COMMAND_EXECUTION]: The skill relies on shell commands to gather information about the repository.
- Evidence: Uses
git diff --name-only,git diff main...HEAD --name-only, andgrepto search within the JSON knowledge graph. These commands are constrained to the local repository and the skill's specific data files.
Audit Metadata