program-portfolio-composition

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists entirely of markdown instructions and formatting templates for the AI agent to follow. No executable scripts, network requests, or sensitive file access patterns were found.
  • [PROMPT_INJECTION]: The skill instructions describe how to aggregate findings from external framework plugins, which creates a surface for potential indirect prompt injection if those sources contain malicious instructions.
  • Ingestion points: Findings are retrieved from multiple external framework plugins as indicated in the skill's description.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included in the reporting templates.
  • Capability inventory: The skill is limited to standard file system access via Read, Glob, and Grep tools.
  • Sanitization: No specific filtering or validation logic is defined for the findings being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:26 PM
Security Audit — agent-trust-hub — program-portfolio-composition