The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or obfuscated content were detected in the skill definition. The skill focuses on legitimate information retrieval and user guidance.
[INDIRECT_PROMPT_INJECTION]: The skill includes tools to ingest data from external sources, which creates a surface for potential indirect prompt injection.
Ingestion points: External data is ingested via WebSearch and Skill(find-docs) as described in the 'Survey the territory' step in SKILL.md.
Boundary markers: Absent. The skill does not specify the use of delimiters or instructions for the agent to ignore commands within retrieved content.
Capability inventory: The skill is limited to information-gathering tools and does not have access to file-writing, shell execution, or other high-privilege capabilities.
Sanitization: No explicit sanitization or filtering of external content is defined.

blindspot