guidelines-advisor
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill identifies a surface for indirect prompt injection due to its core functionality.
- Ingestion points: The skill explores and reads external codebases, including contracts, documentation, and test files (
SKILL.md,ASSESSMENT_AREAS.md). - Boundary markers: The instructions lack explicit boundary markers (e.g., XML tags or delimiters) or specific negative constraints to ignore instructions embedded within the codebase being analyzed.
- Capability inventory: The skill references the use of external tools such as Slither, Echidna, and Foundry (
SKILL.md), which implies the agent may have access to terminal/subprocess capabilities to execute these tools. - Sanitization: There are no instructions to sanitize or validate the content of the ingested files before processing them for recommendations.
- [EXTERNAL_DOWNLOADS] (SAFE): The skill references external security tools (Slither, Echidna, Foundry) and libraries (OpenZeppelin). These are industry-standard resources, and no malicious URLs or automated installation scripts were found.
Audit Metadata