security-threat-model

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill's primary function is to analyze untrusted repository data, which creates a surface for indirect prompt injection. An attacker could embed instructions in the codebase to manipulate the output.
  • Ingestion points: Files within the user-provided repository path are read during the summary and discovery phases.
  • Boundary markers: The skill uses structural headers and role-based instructions in references/prompt-template.md. It does not use unique tokens or XML-style delimiters for ingested content.
  • Capability inventory: The skill utilizes file reading, the ripgrep search tool, and file-write access for the final Markdown report.
  • Sanitization: The instructions explicitly mandate the redaction of secrets, but no specific measures are provided to sanitize or escape potentially malicious prompt instructions in the analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 12:12 AM