The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data from analysis reports which could theoretically contain malicious instructions intended to manipulate the agent's summary or recommendations.
Ingestion points: Data enters the agent's context through the output of metergraph_get_report and metergraph_get_analysis_run (SKILL.md).
Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded commands when processing report content.
Capability inventory: The skill allows the agent to trigger metergraph_start_analysis, an action involving external provider calls and financial expenditure (SKILL.md).
Sanitization: There are no explicit instructions for the agent to sanitize, filter, or validate the content of the reports before generating natural language explanations for the user.

metergraph-analyze