repo-engine

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize content from untrusted external sources (files within the repository being scanned), which creates a surface for indirect prompt injection if those files contain malicious instructions targeting the agent.
  • Ingestion points: The read_file and list_dir tools are used to process arbitrary repository content as specified in the SKILL.md workflow.
  • Boundary markers: The instructions do not explicitly mandate the use of delimiters or warnings for the agent to ignore instructions found within the data it reads.
  • Capability inventory: The skill is restricted to read_file and list_dir capabilities, and network access is explicitly disabled in the metadata (requires_network: false).
  • Sanitization: There is no evidence of content sanitization or filtering before the data is processed by the agent.
  • [SAFE]: The skill's architecture follows the principle of least privilege by using read-only tools and disabling network access, which mitigates the risk of data exfiltration or remote code execution.
  • [SAFE]: The included utility scripts, scripts/validate-output.sh and tests/run-validation.sh, are restricted to local verification of output formats and do not involve suspicious operations, external downloads, or privilege escalation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 05:46 PM