skills/affaan-m/ecc/orch-build-mvp/Gen Agent Trust Hub

orch-build-mvp

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of external specification documents like SDD or PRD files. 1. Ingestion points: Document paths provided as arguments (e.g., in SKILL.md). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded prompts in documents are defined. 3. Capability inventory: The skill has extensive capabilities including scaffolding projects, generating source code via gan-generator, executing evaluation scripts via gan-evaluator, and performing git commits. 4. Sanitization: No automated sanitization is described; the skill relies on manual human-in-the-loop Gate approvals.
  • [COMMAND_EXECUTION]: The skill orchestrates multiple automated tools such as /gan-build and manages automated git commits for the generated features.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 12:55 AM
Security Audit — agent-trust-hub — orch-build-mvp