The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and configuration files providing business analysis guidance. No executable code, scripts, or dangerous commands are present.
[CREDENTIALS_UNSAFE]: The skill includes documentation in references/03-monetization.md that explicitly advises users to keep SDK keys and secrets in secure environment stores rather than hardcoding them, following industry best practices.
[INDIRECT_PROMPT_INJECTION]: The skill involves analyzing external data such as app reviews and competitor claims. However, it specifically instructs the agent in references/04-discovery-listing.md to treat these as untrusted inputs until corroborated, which acts as a proactive mitigation against indirect injection attacks.
[DATA_EXFILTRATION]: There are no network operations or sensitive data access commands. The skill guidelines explicitly warn against automated submission or publication without fresh owner confirmation.

find-niche