The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to ingest and process files matching geographic and spatial patterns.
Ingestion points: Untrusted data enters the agent context from files matching glob patterns like **/*geo*, **/*spatial*, and **/*location* as specified in the 'When This Skill Applies' section of SKILL.md.
Boundary markers: No instructions are provided to use delimiters or specific warnings to ignore instructions embedded in the ingested data.
Capability inventory: The agent context includes access to tools like Bash and GitHub integration (mcp__github__*) as defined in the allowed-tools section of SKILL.md, which represent a significant capability set if exploited.
Sanitization: No sanitization, escaping, or validation logic is specified for the content found within the target files.
[SAFE]: No obfuscation, hardcoded credentials, or unauthorized remote code execution patterns were detected in the skill instructions or metadata.

postgis