caveman-compress

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and compress various inputs, including user queries, build logs, and inter-agent communications. While this represents a surface where untrusted data enters the agent's context, the skill lacks high-privilege capabilities such as network access, system file modification, or shell execution. Its primary function is a benign text transformation for efficiency.
  • Ingestion points: Processes user input and various development artifacts (SKILL.md).
  • Boundary markers: None specified for the processed data.
  • Capability inventory: Text formatting and transformation only.
  • Sanitization: None specified.
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized commands were detected. The skill uses standard instructional language to define a specific persona/style for token optimization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:04 AM
Security Audit — agent-trust-hub — caveman-compress