project-structure

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to read source files from external repositories and summarize them for an LLM. This creates a vulnerability where malicious instructions hidden in code comments or symbol names within the target repository could be processed by the agent.
  • Ingestion points: map.ts walks and reads all source files within a user-defined repoRoot directory.
  • Boundary markers: While the output uses file headers, it lacks explicit delimiters or instructions to the model to ignore embedded instructions in the mapped content.
  • Capability inventory: The skill performs file reads across the target repository and writes output to the local filesystem using node:fs.
  • Sanitization: The script truncates long signatures and doc-comments but does not sanitize or filter the content for prompt injection patterns.
  • [DYNAMIC_EXECUTION]: The script uses dynamic loading to resolve the typescript package from the target repository's environment.
  • Evidence: map.ts uses createRequire with a path derived from the target repository to load the typescript compiler.
  • [COMMAND_EXECUTION]: The skill requires the execution of Node.js scripts to perform its analysis and testing.
  • Evidence: SKILL.md instructs the agent to run node map.ts and selftest.mjs uses execFileSync to run the mapper.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 07:06 PM