skills/unlearndev/skills/triage/Gen Agent Trust Hub

triage

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from git diffs and source code files to generate its report.
  • Ingestion points: The skill reads file contents using the Read tool and consumes output from git diff commands in the SKILL.md file.
  • Boundary markers: The instructions do not specify the use of delimiters or explicit 'ignore embedded instructions' markers to wrap the processed code content.
  • Capability inventory: Capabilities are limited to git (diff, log, status, merge-base, rev-parse), Read, Grep, and Glob. It lacks network access and file-writing capabilities, significantly limiting the potential impact of an injection.
  • Sanitization: No specific content sanitization or validation is performed on the ingested data before analysis.
  • [COMMAND_EXECUTION]: The skill performs shell-based git operations using branch names provided as arguments. The execution environment is restricted to a specific allowlist of git subcommands via the YAML frontmatter configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 04:07 PM
Security Audit — agent-trust-hub — triage