simplify
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The SKILL.md file contains instructions to execute a local Python script for managing additional skills:
python3 scripts/install-external-skills.py --skill deslop --agent codex. This command facilitates the installation and potential execution of additional code modules within the environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary code provided by the user, which could contain malicious instructions. 1. Ingestion points: The agent reads from user-specified files, directories, and branch diffs as described in
references/simplification-workflow.md. 2. Boundary markers: The instructions do not define delimiters to separate user data from agent instructions. 3. Capability inventory: The skill performs actions such as running typecheckers, linters, and tests (references/simplification-workflow.md). 4. Sanitization: There is no evidence of filtering or validation of the input code before it is interpreted.
Audit Metadata