The Agent Skills Directory

[DATA_EXPOSURE]: The skill instructions specifically direct the agent to locate and analyze sensitive configuration files and environment variables to map system behavior. Evidence in SKILL.md triggers searches for os.environ, config[, and settings.. Evidence in references/analysis-checklist.md and references/analysis-process.md include search patterns for **/.env* and ConfigService.
[INDIRECT_PROMPT_INJECTION]: The skill operates by reading and analyzing untrusted source code from external projects, which is a known vector for indirect prompt injection. Ingestion points: The skill uses Read, Grep, and Glob tools to ingest content from the target codebase as described in SKILL.md and references/analysis-process.md. Boundary markers: The instructions do not define delimiters or safety warnings (e.g., "ignore embedded instructions") for the agent when processing file content. Capability inventory: The agent is granted access to Read, Grep, Glob, and Bash tools. Sanitization: There are no requirements or steps provided for sanitizing or escaping the content read from the target codebase before it is processed.

spec-miner