The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and reference data used for reasoning tasks. It contains no executable scripts or system-level commands.
[REMOTE_CODE_EXECUTION]: No patterns for downloading or executing remote code were found. All references are internal to the skill package.
[DATA_EXFILTRATION]: The skill does not access sensitive files, environment variables, or hardcoded credentials, and lacks network capabilities to transmit data externally.
[PROMPT_INJECTION]: The instructions are designed for structured business analysis and do not include techniques to bypass safety guidelines or override system prompts. While the skill ingests user-provided pitches and plans (Ingestion points: Phase 1), it lacks explicit boundary markers or sanitization. However, its capability inventory is empty (no tools, shell access, or network calls), ensuring that any potential indirect injection cannot be exploited.
[NO_CODE]: This skill provides logical frameworks and does not include any Python or Node.js code, minimizing the attack surface to purely informational interactions.

feasibility-assessor