story-short-analyze

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs text analysis within a defined template and does not request or use capabilities that pose a security risk.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user-provided story content for analysis.
  • Ingestion points: User input requested in Phase 1 (SKILL.md) to provide story titles, sources, or content.
  • Boundary markers: The instructions do not define specific delimiters (like XML tags) to isolate untrusted story text from the analysis instructions.
  • Capability inventory: The skill is restricted to generating text-based markdown reports; it does not contain any instructions or scripts to invoke subprocesses, network operations, or file-system writes.
  • Sanitization: No sanitization of the input text is explicitly performed by the skill logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 02:34 AM