acquire-codebase-knowledge

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/scan.py utility invokes git commands through subprocess.run to collect repository insights, such as recent commit history and file churn metrics. These calls are implemented using hardcoded argument lists without shell involvement, which is a standard and secure method for programmatic command execution during local analysis.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and summarize data from an untrusted external source (the user's codebase), including manifest files, configuration templates, and source code comments. This activity inherently exposes the agent to indirect prompt injection if malicious instructions are embedded within the analyzed files. The skill mitigates this risk by requiring the agent to follow a strict evidence-based workflow, forbidding any assumptions, and mandating the use of [TODO] or [ASK USER] markers for any ambiguous or unverifiable information.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 02:11 AM