feature-audit

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and executes the @stevestomp/ohno-cli tool using npx to interact with project tasks. This is a vendor-owned resource associated with the author srstomp.
  • [COMMAND_EXECUTION]: Extensive use of the Bash tool to execute framework detection scripts, file discovery commands, and data processing pipelines across multiple reference files.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill ingests project source code files (e.g., .ts, .tsx, .astro) and PRD requirements retrieved from external CLI tools.
  • Boundary markers: No delimiters or instructions are provided to the agent to ignore potentially malicious instructions embedded within the audited files.
  • Capability inventory: The skill is granted Bash, Grep, Read, and Glob permissions, which allow for full file system access and command execution based on processed data.
  • Sanitization: There is no evidence of content sanitization or validation for the data retrieved from the codebase or the external task system.
  • [DYNAMIC_EXECUTION]: Utilizes node -e within the gap-analysis.md file to dynamically execute JavaScript for parsing and formatting JSON data output from the vendor CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:55 AM