deslop
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of git diffs and source code changes, which could contain malicious instructions designed to influence the agent.
- Ingestion points: The 'Scope and checklist' section in
SKILL.mddescribes reading committed changes, staged/unstaged changes, and untrusted files. - Boundary markers: The instructions do not define specific delimiters or explicit 'ignore embedded instructions' warnings for the code content being processed.
- Capability inventory: The agent is directed to perform file edits and execute git commands (e.g.,
git diff --check). - Sanitization: No explicit sanitization, validation, or filtering of the source code content is described before interpolation or processing.
- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any accompanying scripts or executables.
Audit Metadata