skills/awjreynolds/gadd/gaps-validate/Gen Agent Trust Hub

gaps-validate

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (scripts/validate-gaps.py and scripts/validate-gaps-implementation.py) using python3. It passes user-supplied arguments (file paths) directly to these shell commands, which poses a potential command injection risk if the agent does not properly escape shell-active characters.
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface (Category 8):
  • Ingestion points: The skill reads multiple external data sources including gaps/README.md, JSON schemas, example YAML configuration files, and agent-skills.json (SKILL.md).
  • Boundary markers: Absent. There are no instructions to use delimiters or ignore embedded instructions within the ingested data.
  • Capability inventory: The skill has the capability to execute shell commands via the python3 subprocesses (SKILL.md).
  • Sanitization: Absent. There is no evidence of content validation or escaping before the data is processed or before arguments are passed to the scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 06:45 PM
Security Audit — agent-trust-hub — gaps-validate