dependency-coordinator

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits a potential indirect prompt injection surface as it ingests project plans and tech-stack profiles (e.g., .claude/profile.yaml) which are external data sources. (1) Ingestion points: Project plans and .claude/profile.yaml referenced in SKILL.md; (2) Boundary markers: None explicitly defined in the instructions; (3) Capability inventory: Bash, Write, Edit, Glob, and Read tools; (4) Sanitization: The skill relies on the specific task of generating structured dependency manifests to constrain the output rather than explicit sanitization logic.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run package manager verification commands like pnpm install --dry-run and cargo check. These commands are standard for development environments and are used with safety flags to prevent actual modification of the environment or execution of third-party scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:32 PM