dependency-updater
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill evaluates untrusted data from project repositories and external documentation, presenting a surface for indirect prompt injection.
- Ingestion points: Project manifests, source code, CI workflows, and external documentation (Step 2, 3, 4, 5).
- Boundary markers: The instructions explicitly state to treat third-party content as research material that should not override skill behavior.
- Capability inventory: The skill can execute shell commands found in the repository for verification (Step 8).
- Sanitization: The skill relies on natural language boundary instructions.
- [COMMAND_EXECUTION]: The Verification Plan involves running build and test commands identified within the repository's own configuration files and scripts.
- [EXTERNAL_DOWNLOADS]: The skill performs research by fetching information from official package registries and documentation repositories.
Audit Metadata