The Agent Skills Directory

[SAFE]: No security issues were identified during the audit. The skill consists purely of stylistic and structural guidelines for improving technical documentation, PR descriptions, and commit messages.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns or unverifiable dependencies were found. The skill does not perform any network operations or package installations.
[DATA_EXFILTRATION]: No data exfiltration risks were detected. The skill does not access sensitive local files or transmit data to external servers.
[PROMPT_INJECTION]: The instructions do not contain patterns designed to bypass AI safety filters or override system constraints. It provides legitimate instructional guidance for a specific task (technical writing).
[OBFUSCATION]: No obfuscated code, encoded strings, or hidden characters were found in the provided files.
[PRIVILEGE_ESCALATION]: The skill does not attempt to acquire elevated permissions or perform administrative tasks.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user-provided text (such as RFCs or PR descriptions), it does not possess any dangerous capabilities (like shell execution or network access) that could be exploited via malicious input data.

technical-writing