arkweb-spec-gen

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed for local documentation management, automating the creation of project specifications and task lists based on local files.
  • [PROMPT_INJECTION]: The skill processes content from multiple external markdown documents which represents an attack surface for indirect prompt injection.
  • Ingestion points: Reads from proposal.md, requirement.md, design.md, review.md, analysis.md, and template files located in the {DOCS_REPO} directory.
  • Boundary markers: Absent; no explicit delimiters or instructions to ignore embedded commands within the source documents are provided.
  • Capability inventory: File system read and write operations are used to aggregate and store documentation.
  • Sanitization: Absent; the skill extracts and reformats content from input documents without filtering or sanitizing for potentially malicious payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 09:00 AM
Security Audit — agent-trust-hub — arkweb-spec-gen