product-strategy

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (ls) across several potential installation directories (e.g., ~/.claude/skills/, ~/.agent/skills/) to identify which companion skills are currently installed on the host system.
  • [EXTERNAL_DOWNLOADS]: The instructions direct the agent to recommend the installation of additional remote resources from the author's repository (AbsolutelySkilled) using the npx skills add command if specific companion skills are missing.
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection. Ingestion points: User inputs in vision and roadmap templates in SKILL.md. Boundary markers: Absent. Capability inventory: Local reconnaissance via shell (ls). Sanitization: Absent. Malicious input in these fields could be used to influence agent responses or trigger unauthorized command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 01:04 PM
Security Audit — agent-trust-hub — product-strategy