NYC

accelint-readme-writer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) because it recursively parses and analyzes files within a codebase, including source code, comments, and tests, which are untrusted data sources.
  • Ingestion points: The skill reads source files, entry points, and JSDoc/TSDoc comments as specified in references/codebase-analysis.md.
  • Boundary markers: Absent; there are no instructions for the agent to use delimiters or ignore embedded instructions when reading untrusted code data.
  • Capability inventory: The skill allows broad read access to the workspace and generates markdown documentation based on the findings.
  • Sanitization: Absent; the skill does not include steps to sanitize or filter extracted code strings or comments before including them in the generated README.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:04 PM