The Agent Skills Directory

[SAFE]: The skill and its associated reference files do not contain any malicious patterns. The code provided consists of standard Python templates for Discord and Telegram bots using well-known libraries.- [PROMPT_INJECTION]: Instructions are focused on technical bot development and do not attempt to bypass agent constraints or safety filters.- [DATA_EXFILTRATION]: No unauthorized data access or transmission was found. The connection strings for PostgreSQL and Redis are generic placeholders (e.g., localhost), and the security checklist correctly advises against committing tokens to version control.- [REMOTE_CODE_EXECUTION]: The skill uses standard, verifiable dependencies for bot development. There is no usage of dangerous functions like eval() or remote script execution via curl|bash.- [INDIRECT_PROMPT_INJECTION]: While the skill builds bots that process user-generated content, it includes specific mitigations like input sanitization and parameterized queries in its security checklist. Evidence: 1. Ingestion points: Message handlers in references/platform-templates.md. 2. Boundary markers: Security checklist mentions validation. 3. Capability inventory: Uses Bash and WebFetch for development tasks. 4. Sanitization: Specifically recommended in the security checklist section of SKILL.md and platform-templates.md.

bot-developer