app-description-writer

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's instructions and templates are entirely focused on text generation for app marketing. No evidence of prompt injection, data exfiltration, or unauthorized command execution was found.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided data regarding app features and reviews to generate marketing descriptions. This creates a surface for indirect prompt injection if malicious instructions are provided in the input data.
  • Ingestion points: User responses to the 'Information Gathering' section in SKILL.md (e.g., App Basics, Key Features, Social Proof).
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands in the user-provided data.
  • Capability inventory: The skill has access to file system tools (Write, Edit, Glob, Grep), which could be misused if the agent obeys instructions embedded in the ingested data.
  • Sanitization: No input validation or sanitization logic is present to filter user-supplied content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 01:18 PM
Security Audit — agent-trust-hub — app-description-writer