skills/sunic4/dev-skills/cc-req/Gen Agent Trust Hub

cc-req

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell commands including find and grep to perform file system operations. Specifically, it uses find with the -exec head pattern to scan existing requirement documents and grep to identify downstream dependencies for change propagation. These operations are scoped to the project's wiki/ directory and support legitimate documentation management tasks.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests and processes content from local Markdown files that could contain untrusted instructions.
  • Ingestion points: Documentation files in wiki/requirements/ and other files within the wiki/ directory are read during de-duplication checks and dependency tracking steps.
  • Boundary markers: The skill does not implement specific boundary markers or 'ignore' instructions when presenting the contents of ingested files to the agent.
  • Capability inventory: The skill allows the agent to execute shell commands (find, grep) and perform file system writes within the project's wiki/ folder.
  • Sanitization: Content read from the local files is processed without explicit sanitization or validation against structural rules.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 06:03 AM