skills/moeller-projects/skills/bluf/Gen Agent Trust Hub

bluf

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a set of formatting and interaction guidelines designed to improve efficiency and clarity. No malicious code, obfuscation, or unauthorized data access patterns were detected. All technical examples in the documentation use well-known, legitimate libraries and standard developer tooling commands.- [INDIRECT_PROMPT_INJECTION]: The skill defines rules for processing and reformatting data from various sources. It mitigates potential injection risks by enforcing a "compression boundary" that preserves the integrity of code blocks, commands, and technical identifiers.
  • Ingestion points: Processes user queries and file content via the read_file tool.
  • Boundary markers: Explicitly mandates the preservation of safety qualifiers and technical data in SKILL.md.
  • Capability inventory: Utilizes the read_file tool for context gathering as defined in the skill metadata.
  • Sanitization: Requires technical terms and code to remain byte-exact and unchanged during the compression process.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 11:26 AM