pmf-analysis

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the git log command as a subprocess to evaluate the project's development history, commit frequency, and feature focus.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and analyzes untrusted data from the codebase (such as README files, marketing copy, and source code) without using boundary markers or sanitization. * Ingestion points: The skill reads project READMEs, package metadata, and source code files (SKILL.md). * Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the ingested codebase files. * Capability inventory: The agent has the ability to execute shell commands (git log) and write files to the project directory (docs/pmf-analysis.md). * Sanitization: The skill does not perform validation or filtering on the content it reads from the codebase before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:57 AM
Security Audit — agent-trust-hub — pmf-analysis