loom-dependency-scan

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute various package manager audit commands and vulnerability scanners (e.g., npm audit, pip-audit, cargo audit, govulncheck) as part of its core functionality.\n- [EXTERNAL_DOWNLOADS]: The instructions directory the agent to install well-known security utilities and SBOM generators, such as @cyclonedx/cyclonedx-npm, cargo-cyclonedx, and cyclonedx-bom, from official package registries.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads and processes data from external project manifest files which are considered untrusted input.\n
  • Ingestion points: Project manifest and lock files (e.g., package.json, requirements.txt, Cargo.lock) are identified and read using the Glob and Read tools.\n
  • Boundary markers: There are no instructions for the agent to use specific delimiters or to ignore embedded instructions within the manifest files being scanned.\n
  • Capability inventory: The skill has access to Bash for command execution and file system tools (Read, Grep, Glob) for data ingestion.\n
  • Sanitization: The instructions do not specify any validation or sanitization steps for the content parsed from the manifest files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 07:35 AM
Security Audit — agent-trust-hub — loom-dependency-scan