ln-653-runtime-performance-auditor

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external source code which creates a potential surface for indirect prompt injection.
  • Ingestion points: The skill ingests codebase content via Read, Grep, and mcp__hex-line__read_file as described in SKILL.md.
  • Boundary markers: There are no explicit instructions in SKILL.md to utilize boundary markers or delimiters when reading the content of files to be audited.
  • Capability inventory: The skill utilizes the Bash tool for pattern matching and performs file write operations to create markdown reports (SKILL.md).
  • Sanitization: No sanitization or filtering of the ingested source code is performed before analysis as per the workflow in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 12:53 PM