impress-me
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to aggregate and process information from untrusted external sources and the local codebase, which establishes a surface for indirect prompt injection where malicious content could influence agent behavior. * Ingestion points: Web content, local codebase, and MCP resources (found in SKILL.md). * Boundary markers: Absent; there are no delimiters or instructions to treat ingested data as untrusted. * Capability inventory: Broad; the skill encourages the use of 'any available tools' (found in SKILL.md). * Sanitization: Absent; no validation or filtering is defined for the researched findings.
- [NO_CODE]: The skill consists entirely of natural language instructions and does not include any executable scripts or configuration files.
Audit Metadata