skills/khoahyh/skills/subtract/Gen Agent Trust Hub

subtract

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to read and modify codebase content, which creates a natural surface for indirect prompt injection. Malicious content within a processed repository could attempt to influence the agent's simplification logic.
  • Ingestion points: The agent surveys all repository content, including tracked and untracked files (SKILL.md).
  • Boundary markers: The instructions do not specify delimiters or warnings to ignore embedded instructions in the files being analyzed.
  • Capability inventory: The skill authorizes the agent to delete files, artifacts, and tests, and to modify code structures like inlining or collapsing duplicates.
  • Sanitization: The skill relies on 'subtraction judgment' and verification steps rather than technical sanitization of the input data.
  • [NO_CODE]: The skill contains only instructional documentation (markdown) and does not include any scripts, executable code, or package manifests.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 05:40 AM
Security Audit — agent-trust-hub — subtract