suparank/create
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- Prompt Injection (LOW): The skill ingests research data from
.claude/suparank-session.jsonwhich originates from untrusted external sources, creating a surface for indirect prompt injection. \n - Ingestion points:
.claude/suparank-session.json(research_results). \n - Boundary markers: Absent; the agent is instructed to directly follow the research and planning results. \n
- Capability inventory: Directory creation (
mkdir) and file writing (article.md,metadata.json, session updates). \n - Sanitization: None detected for the interpolated research data. \n- Command Execution (LOW): The skill instructs the agent to execute shell commands for directory management. \n
- Evidence: Explicit instruction to run
mkdir -pusing a path derived from a generated slug.
Audit Metadata