cc-changelog

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script scripts/fetch-cc-changelog.sh with various arguments to fetch updates and update its version state.
  • [EXTERNAL_DOWNLOADS]: The skill is designed to fetch changelog data from external sources via a local script, though the specific remote URL is not defined in the skill instructions.
  • [PROMPT_INJECTION]: The skill processes externally sourced changelog data, which introduces a potential surface for indirect prompt injection. 1. Ingestion points: Content returned by scripts/fetch-cc-changelog.sh. 2. Boundary markers: Absent; instructions do not specify delimiters to separate external content from agent instructions. 3. Capability inventory: Execution of bash scripts and extensive read access to repository files including configuration and hook definitions. 4. Sanitization: Absent; no validation or escaping of the fetched changelog content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 04:30 PM
Security Audit — agent-trust-hub — cc-changelog