candid-optimize
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands including
find,ls,mkdir,jq, andgit branchto analyze the repository structure, validate JSON configuration, and identify branching strategies.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes untrusted data from local markdown and configuration files.\n - Ingestion points: Technical.md, .candid/config.json, ~/.candid/config.json, and the decision register markdown file.\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.\n
- Capability inventory: The skill utilizes the
EditandWritetools to modify local files and executes several shell commands (ls,find,mkdir,jq,git).\n - Sanitization: The skill does not perform sanitization or validation of content within the analyzed markdown files before processing.
Audit Metadata