The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill is configured to locate and read sensitive environment and configuration files.
Evidence: Glob: **/.env* and Grep('os\\.environ|config\\[|settings\\.', include='*.py') found in SKILL.md and references/analysis-process.md.
Risk: This behavior allows the agent to access secrets, API keys, and environment variables stored within the codebase being analyzed.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the codebase being analyzed, creating a surface for indirect prompt injection.
Ingestion points: The skill reads and searches project files using the Read, Glob, and Grep tools as defined in the SKILL.md workflow.
Boundary markers: Absent; there are no instructions or delimiters provided to ensure the agent disregards natural language instructions found within code comments or documentation.
Capability inventory: The skill utilizes Bash, Read, Glob, and Grep tools for its operations.
Sanitization: Absent; the skill does not filter or validate the content of the analyzed files before the agent processes them.
[COMMAND_EXECUTION]: The skill uses shell-based tools to perform complex searches and codebase mapping.
Evidence: The workflow and references rely on executing searches via Grep and Glob tools to extract information from the filesystem.

spec-miner