The Agent Skills Directory

[DATA_EXFILTRATION]: The skill instructs the agent to search for and read sensitive configuration files including environment files (e.g., **/.env*) as part of its exploration phase. This provides a direct path for the exposure of hardcoded credentials, API keys, and other secrets located within the analyzed codebase.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it is designed to ingest and process content from untrusted external codebases.
Ingestion points: The agent is instructed to use Read, Grep, and Glob tools to process any file within the target project directory (referenced in SKILL.md and references/analysis-checklist.md).
Boundary markers: There are no instructions providing delimiters or warnings to ignore or isolate instructions that may be embedded in the code, comments, or documentation of the system being analyzed.
Capability inventory: The skill possesses the Bash tool and file system tools (Read, Glob, Grep), which could be misused if the agent follows malicious instructions found during analysis.
Sanitization: The workflow lacks any sanitization or validation of the data ingested from the external codebase before it is processed by the agent.

spec-miner