impl

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes external documentation to guide its core logic.
  • Ingestion points: The agent is instructed to read requirements, task cards, PRDs, and API lists from the environment or conversation to decompose implementation units (SKILL.md).
  • Boundary markers: The instructions lack explicit boundary markers or directives to ignore instructions embedded within the ingested data sources.
  • Capability inventory: The skill possesses capabilities to modify the codebase and execute git commands, including atomic-commit, git worktree, and git cherry-pick (SKILL.md, ISOLATION.md).
  • Sanitization: There is no mention of sanitization, validation, or filtering of the content retrieved from external documents to prevent malicious instruction override.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 08:08 AM
Security Audit — agent-trust-hub — impl