rules

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists entirely of a markdown documentation file and does not contain any executable scripts, binaries, or logic.- [SAFE]: No malicious patterns such as credential harvesting, unauthorized network access, or persistence mechanisms were found in the documentation.- [PROMPT_INJECTION]: The skill describes an architecture that ingests external instruction files, representing a surface for indirect prompt injection if those files are controlled by an attacker.
  • Ingestion points: Documentation indicates the plugin reads from .sisyphus/rules, .claude/rules, .cursor/rules, and .github/instructions.
  • Boundary markers: None are specified in the provided documentation to isolate rule content from system prompts.
  • Capability inventory: The skill provides informational context only and does not define any active tools or shell capabilities.
  • Sanitization: No filtering or validation mechanisms for external rule content are described in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 02:20 PM
Security Audit — agent-trust-hub — rules