Skills
Navigate
skills/jeremylongshore/tons-of-skills-marketplace/openevidence-performance-tuning/Gen Agent Trust Hub

openevidence-performance-tuning

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external clinical queries and context objects which could potentially contain malicious instructions embedded within medical data.
  • Ingestion points: The question string and ClinicalContext object are ingested in the functions defined in references/implementation.md.
  • Boundary markers: There are no explicit delimiters or specific instructions to the agent to ignore embedded commands within the input data.
  • Capability inventory: The skill is authorized to use Read, Write, Edit, and Grep tools as specified in the allowed-tools metadata in SKILL.md.
  • Sanitization: The optimizeQuestion function in references/implementation.md performs basic string cleanup (removing polite phrasing and trimming whitespace) but does not provide security-focused sanitization against prompt injection payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 10:05 PM
Security Audit — agent-trust-hub — openevidence-performance-tuning