Skills
skills/jeremylongshore/claude-code-plugins-plus-skills/optimizing-prompts/Gen Agent Trust Hub

optimizing-prompts

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The file assets/example_prompts.md contains common prompt injection phrases such as "Ignore previous instructions". Analysis confirms these are benign examples used for demonstrating how to detect malicious patterns, rather than attempts to override agent behavior.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection.
  • Ingestion points: User-provided prompts intended for optimization are ingested as primary data via the SKILL.md workflows.
  • Boundary markers: No explicit boundary markers or isolation instructions are present to separate user-provided content from the agent's task instructions.
  • Capability inventory: The skill has access to high-privilege tools including Bash, Write, Edit, and Grep as defined in SKILL.md.
  • Sanitization: There is no documented evidence of sanitization or filtering of the input prompts before they are processed by the agent logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 08:02 AM