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, and git branch to 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 Edit and Write tools 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
Risk Level
SAFE
Analyzed
Feb 26, 2026, 03:25 PM