The Agent Skills Directory

[PROMPT_INJECTION]: The skill analyzes untrusted data from the user's project files, creating a surface for indirect prompt injection.\n
Ingestion points: docs/prd.md, CLAUDE.md, and stack configuration files in templates/stacks/ are read to extract feature and stack information.\n
Boundary markers: Absent; the instructions do not specify the use of delimiters or warnings to the agent to ignore instructions embedded within the ingested files.\n
Capability inventory: The skill's capabilities are limited to local file system operations using Read, Grep, Glob, and Write to create markdown files in a legal/ directory.\n
Sanitization: Absent; there is no evidence of content validation or escaping of the data read from the project files before it is processed by the agent.\n- [NO_CODE]: The skill is composed entirely of markdown instructions and configuration and does not include any accompanying executable scripts or binaries.

solo-legal