copywriting

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill contains no malicious code, obfuscation, or unauthorized data access patterns. It provides standard instructional content for conversion copywriting.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local context files, which represents a potential injection surface, though it lacks the capabilities to execute malicious payloads.
  • Ingestion points: The skill reads from .agents/product-marketing-context.md or .claude/product-marketing-context.md (SKILL.md).
  • Boundary markers: No explicit delimiters are used to separate the ingested context from the agent instructions.
  • Capability inventory: The skill is limited to text generation. There are no subprocess calls, environment modifications, network operations, or file-writing tools used.
  • Sanitization: No sanitization or filtering of the ingested file content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 02:58 PM
Security Audit — agent-trust-hub — copywriting