skills/mblode/agent-skills/agents-md/Gen Agent Trust Hub

agents-md

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform validation by running shell commands discovered in the repository's configuration files (e.g., package.json, Makefile). This includes executing commands for development, testing, building, and linting. Evidence: SKILL.md Step 6 specifies: "Smoke-run core commands (dev, test, build, lint/typecheck) where the environment allows; otherwise verify the script exists in the manifest..."
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repository instruction files (AGENTS.md, CLAUDE.md) and manifests (package.json, Makefile) which are used to define the agent's behavior and environment. Ingestion points: SKILL.md Step 1 uses find and ls to discover and read instruction files from the current repository. Capability inventory: The skill has the ability to execute shell commands, read/write to the filesystem, and modify agent instructions. Boundary markers: No specific boundary markers or "ignore" instructions are used when interpolating file content. Sanitization: No explicit sanitization or validation of the ingested instruction content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 04:07 AM