skills/agentivestack/skills/spec/Gen Agent Trust Hub

spec

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill does not perform high-risk operations such as network requests, credential access, or arbitrary command execution.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes codebase content and existing documentation to generate new specifications.
  • Ingestion points: Reads project documentation (e.g., docs/CONTEXT_MAP.md, CLAUDE.md) and explores the codebase to understand the current state of features.
  • Boundary markers: No explicit delimiters or instructions are used to isolate untrusted codebase content from the agent's instructions.
  • Capability inventory: The skill can write files to the docs/contexts/ directory and update documentation files like UBIQUITOUS_LANGUAGE.md.
  • Sanitization: There is no evidence of sanitization or validation of the content read from the codebase before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 10:36 PM