The Agent Skills Directory

[SAFE]: The skill's functionality is centered on local project analysis and configuration. It uses a specific CLI tool (pythia) to scan existing database schemas and write convention files to the .pythia/ directory. No external network operations, credential access, or unauthorized persistence mechanisms were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes data from external sources.\n
Ingestion points: Database object names retrieved via pythia conventions --scan and developer documents (wiki pages, standards documents) mentioned in the workflow.\n
Boundary markers: The instructions do not specify explicit delimiters or boundary markers for the ingested data.\n
Capability inventory: The skill executes pythia commands for scanning and verification and writes configuration/markdown files to the local filesystem.\n
Sanitization: There is no mention of explicit sanitization or filtering for the external content before it is processed.

pythia-conventions