yagni
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional text and code examples for software development best practices. No malicious code, obfuscated content, or unauthorized commands are present in the provided file.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local stack context files ('.agents/stack-context.md') and perform web searches. While these are ingestion points for potentially untrusted data, the skill does not provide any actionable tools or dangerous capabilities (such as file writes, arbitrary command execution, or network exfiltration) that would allow an indirect prompt injection to perform harmful actions. Evidence Chain: 1. Ingestion points: .agents/stack-context.md and web search. 2. Boundary markers: Absent. 3. Capability inventory: None detected across the skill. 4. Sanitization: Absent.
Audit Metadata