investor-update-generator

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a local productivity tool for validating markdown files. It does not perform network operations or access sensitive system files.
  • [COMMAND_EXECUTION]: The skill utilizes a local Python script (scripts/investor_update_validator.py) to analyze a user-provided file (update.md). This execution is restricted to the local environment and the script uses only standard Python libraries (argparse, json, re, sys, pathlib).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external text data (investor update drafts).
  • Ingestion points: The investor_update_validator.py script reads the content of a user-specified markdown file.
  • Boundary markers: The skill does not explicitly use boundary markers when presenting the validator's output to the agent.
  • Capability inventory: The script's capabilities are limited to reading local files and printing structural analysis to standard output. It lacks network, shell execution (beyond being called by the agent), or file-write permissions.
  • Sanitization: The script performs regex-based pattern matching for structural validation but does not execute or interpret the content of the markdown file as code or instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 10:35 PM
Security Audit — agent-trust-hub — investor-update-generator