specs-extractor

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a set of high-quality instructions for documenting software behavior. It does not utilize remote scripts, external dependencies, or network-enabled tools.
  • [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection as its primary function is to ingest and synthesize behavior from external, potentially untrusted source code and configuration files.
  • Ingestion points: The agent is instructed to read application code, database schemas, migrations, test files, and configuration files located in the user's environment.
  • Boundary markers: The instructions lack explicit delimitation or 'ignore instructions' directives for the agent when processing the content of the analyzed files.
  • Capability inventory: The agent has the capability to read local project files and write resulting markdown files to a designated specs/ directory on the local file system.
  • Sanitization: No sanitization or content validation mechanisms are specified for the data extracted from the codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 06:56 PM
Security Audit — agent-trust-hub — specs-extractor