dependency-audit
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute native package manager CLI tools, including npm, yarn, pnpm, bun, composer, pip-audit, safety, cargo-audit, govulncheck, pod-audit, and bundle-audit. These tools are used for their intended purpose of identifying and optionally fixing security vulnerabilities in project dependencies (SKILL.md, audit-commands.md).
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests and processes data from external sources, which constitutes an attack surface.
- Ingestion points: Data is ingested from external vulnerability advisory databases via the standard output of local audit tools (SKILL.md, audit-commands.md).
- Boundary markers: The provided files do not include explicit boundary markers or instructions for the agent to ignore or isolate instructions that might be embedded in vulnerability descriptions or advisory content.
- Capability inventory: The skill combines the reading of external data with the capability to execute shell commands and modify the local file system through package updates (SKILL.md).
- Sanitization: There are no documented procedures for sanitizing or filtering the content of external advisories before the agent processes them or incorporates them into report templates.
Audit Metadata