components-version-badge

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses dynamic context injection (the ! syntax) to execute shell commands like find and jq upon loading. These commands are used to identify the project's tech stack and version and are restricted to the local project directory.
  • [COMMAND_EXECUTION]: The instructions require the creation and execution of a local script (scripts/parse-changelog.mjs) to parse the project's changelog during the build process.
  • [PROMPT_INJECTION]: The skill processes content from CHANGELOG.md, which is an untrusted external source, presenting a surface for indirect prompt injection.
  • Ingestion points: CHANGELOG.md is read and parsed by the generated script described in SKILL.md.
  • Boundary markers: No delimiters or instructions to ignore embedded commands are specified for the changelog content.
  • Capability inventory: The skill has access to Bash, Write, and Edit tools as defined in the allowed-tools frontmatter.
  • Sanitization: The skill does not implement sanitization or validation for the content extracted from the changelog.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 01:17 AM