skills/yogsoth-ai/de-anthropocentric-research-engine/estimate-effective-evidence-count/Gen Agent Trust Hub
estimate-effective-evidence-count
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of instructional markdown and schema definitions without any associated scripts, executables, or command-line operations.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing user-provided evidence_paths. Because the skill does not grant the agent access to any tools or execute any code, the risk of instruction override via this input is negligible. Ingestion points: evidence_paths in SKILL.md; Boundary markers: None; Capability inventory: None; Sanitization: None.
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill instructions or metadata.
Audit Metadata