map-research-landscape
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 markdown instructions and YAML metadata without any attached scripts, executables, or code files.
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill follows standard task orchestration patterns by delegating work to other skills.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an input contract that ingests external data (research_intent, seed_evidence). This creates a theoretical indirect prompt injection surface; however, the skill defines no direct system capabilities or tools that could be exploited, relying instead on host-selected evidence acquisition and platform safety guardrails.
- Ingestion points: The 'research_intent' and 'seed_evidence' fields in the input contract.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the execution protocol.
- Capability inventory: The skill delegates all actions to sub-skills like 'generate-candidate-directions' and 'synthesize-field-panorama' rather than executing system-level tools directly.
- Sanitization: No explicit sanitization or validation of the input evidence is described.
Audit Metadata