triage-dependencies

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is local security triaging and it does not contain malicious patterns such as credential theft, persistence mechanisms, or obfuscation.
  • [COMMAND_EXECUTION]: The workflow involves using grep to search through local project source code for library imports. This is a standard, read-only development operation restricted to the project root directory.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it ingests untrusted data from project source files and dependency manifests. * Ingestion points: Local project source files in <project-root> and the dependency list in <model-dir>/project.yaml. * Boundary markers: None are specified to protect the agent from instructions embedded within the analyzed code. * Capability inventory: The skill can read local files and write a tracking report to <tracking-dir>/coverage.yaml. It lacks network access and arbitrary shell execution capabilities. * Sanitization: No sanitization or validation of the contents of the ingested project files is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 10:39 AM
Security Audit — agent-trust-hub — triage-dependencies