marketing-ideas

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions in SKILL.md direct the agent to read untrusted data from local context files (.agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md). This creates a vulnerability surface where an attacker with write access to the repository could embed malicious instructions that the agent might follow when these files are read into context.
  • Ingestion points: Found in SKILL.md, where the agent is told to check for and read product marketing context files.
  • Boundary markers: Absent. The instructions do not define clear delimiters or provide warnings to the agent to disregard embedded instructions within the ingested files.
  • Capability inventory: The skill is purely informational; it does not include any scripts, tools, or requested permissions for file writing, network access, or command execution.
  • Sanitization: Absent. The skill does not provide instructions for the agent to filter or sanitize the external data before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:25 PM
Security Audit — agent-trust-hub — marketing-ideas