analyze-codebase-for-mcp

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes content from arbitrary external codebases that may contain malicious instructions designed to manipulate the agent.
  • Ingestion points: Content is read from a user-provided codebase path using Glob, Grep, and Read tools (SKILL.md).
  • Boundary markers: There are no boundary markers or instructions to ignore instructions embedded within the analyzed source code files to prevent accidental execution of commands found in documentation or comments.
  • Capability inventory: The skill has access to Bash, Grep, Glob, and Read tools, and it generates/writes files (mcp-tool-spec.yml) to the local filesystem based on analyzed content (SKILL.md).
  • Sanitization: No sanitization or validation of the ingested code content is performed before the agent processes and uses it to draft tool specifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 11:56 PM