The Agent Skills Directory

[COMMAND_EXECUTION]: Invokes local Python scripts (audit-geo.py, check-hedge-density.py, generate-agentfacts.py) stored in the skill's script directory to perform technical and content analysis.
[DATA_EXFILTRATION]: Performs network requests via curl to retrieve technical headers (Content-Length) from target websites. This is used strictly for size validation as part of the GEO audit workflow.
[PROMPT_INJECTION]: Contains an indirect prompt injection surface as the skill processes external content from URLs. Ingestion points: The scripts audit-geo.py and check-hedge-density.py accept external URLs as input for analysis. Boundary markers: None; the skill does not explicitly delimit untrusted data or instruct the agent to ignore instructions embedded in the target content. Capability inventory: Subprocess execution of Python scripts and network access via curl are the primary capabilities. Sanitization: The skill documentation does not mention sanitization or validation of the fetched content beyond technical metric extraction.

geo-optimizer