stand-general
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to automatically ingest and treat instructions from repository-level files (AGENTS.md or CLAUDE.md) as binding context for the session.\n
- Ingestion points: Target repository root files AGENTS.md and CLAUDE.md.\n
- Boundary markers: The skill instructs the agent to treat these instructions as "binding" and does not specify any delimiters or warnings to ignore malicious instructions embedded within them.\n
- Capability inventory: While this skill is primarily instructional, it orchestrates the agent's use of several other skills (lint, test, commit, pr, coderabbit, greptile) which involve shell command execution and network operations.\n
- Sanitization: No sanitization, validation, or human-in-the-loop verification is mentioned for the content of these external files.
Audit Metadata