The Agent Skills Directory

[DATA_EXPOSURE_AND_EXFILTRATION]: The skill contains explicit instructions to locate and potentially read sensitive configuration files and environment variable definitions that are known to contain credentials.
Evidence: The 'references/analysis-process.md' and 'references/analysis-checklist.md' files instruct the agent to use Glob: **/.env* to find environment files.
Evidence: The 'SKILL.md' file suggests using Grep to discover configuration usage via os\.environ|config\[|settings\..
[INDIRECT_PROMPT_INJECTION]: The skill is highly vulnerable to indirect prompt injection because it is designed to ingest and process undocumented or legacy codebases which are considered untrusted data.
Ingestion points: Codebase files accessed via Read, Grep, and Glob tools across all project directories as defined in 'references/analysis-process.md'.
Boundary markers: Absent. The skill does not provide instructions for the agent to use delimiters or ignore embedded instructions within the processed code.
Capability inventory: The agent has access to Bash, Read, Grep, and Glob, enabling it to execute commands or read any file in the accessible environment.
Sanitization: Absent. There is no mention of filtering, escaping, or validating the content of the files before they are processed by the agent.

spec-miner