The Agent Skills Directory

[Prompt Injection] (SAFE): The skill instructions do not contain patterns intended to override agent behavior or bypass safety filters. Phrases like 'IMPORTANT' are used in a benign, instructional context.- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network operations (curl, wget) are present in the skill definition.- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not download or execute remote scripts. References to tools like '2to3' or 'npm test' are provided as advice for the user to perform, not as commands for the agent to execute automatically.- [Indirect Prompt Injection] (LOW): This skill is vulnerable to indirect prompt injection as it processes untrusted user code (Ingestion points: User Request/Code snippets). It lacks explicit boundary markers to separate untrusted data. However, the skill has no functional capabilities (Capability inventory: None/Text-only) such as file writing or network access, and thus poses no significant risk. Sanitization is not implemented as it is a pure-prompt skill.- [Obfuscation] (SAFE): No Base64, zero-width characters, or other encoding techniques were found.

migration-upgrader