project-skill-audit

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, potentially untrusted sources, creating a surface for indirect prompt injection attacks.
  • Ingestion points: The skill explicitly instructs the agent to read repository documentation (README.md, AGENTS.md), memory index files (MEMORY.md), rollout summaries, and raw session logs (sessions/*.jsonl). These files may contain instructions or data from previous sessions that could be used to influence the agent's current behavior.
  • Boundary markers: No specific instructions are provided to the agent to treat the content of these files as data only or to ignore any embedded instructions or prompts found within them.
  • Capability inventory: The skill workflow utilizes file reading and the rg (ripgrep) tool for information retrieval. It does not exhibit capabilities for file-writing, network exfiltration, or arbitrary code execution.
  • Sanitization: There are no defined steps for sanitizing, validating, or escaping the external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:26 AM
Security Audit — agent-trust-hub — project-skill-audit