supply-chain-risk-auditor

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external dependency repositories which could contain malicious instructions.\n- Ingestion points: Project dependency names and metadata (READMEs, issue counts) retrieved via the gh tool (SKILL.md).\n- Boundary markers: The skill lacks explicit instructions to treat external data as untrusted or to ignore commands embedded within that data.\n- Capability inventory: The skill uses Bash, Write, and the gh CLI tool, providing a functional surface for an attacker to influence if instructions in dependency data are followed.\n- Sanitization: No sanitization or validation of the data retrieved from external repositories is performed before it is used in report generation or shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 11:16 AM
Security Audit — agent-trust-hub — supply-chain-risk-auditor