skills/sztadii/agent-skills/proof/Gen Agent Trust Hub

proof

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: This skill presents an attack surface for indirect prompt injection as it ingests and processes untrusted data from repositories.
  • Ingestion points: The skill reads local code, commit messages, PR descriptions, and test outputs (SKILL.md).
  • Boundary markers: The instructions do not define any delimiters or warnings to prevent the agent from following instructions embedded in the code or logs.
  • Capability inventory: The skill is authorized to run shell commands for tests (static, unit, integration, e2e) and utilize browser MCP tools for UI inspection (SKILL.md).
  • Sanitization: There is no requirement or implementation for sanitizing external inputs before they are processed by the agent.
  • [COMMAND_EXECUTION]: The workflow involves running repository-provided checks and commands which can execute arbitrary code in the local environment (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 05:35 PM