Security audit
Security checks for vulnerabilities and agentic risk
The skill is not clearly malicious, but it asks for powerful file and shell permissions while describing a broad, poorly scoped workflow that does not stay tied to finishing a development branch.
Review this skill before installing. It does not show evidence of a hidden payload, but it grants broad local file and shell authority and mentions credentials and external services without a clear branch-finishing workflow. Use it only in a controlled repository, avoid providing secrets unless the exact need is clear, and require confirmation before file mutations, shell commands, or network/API use.
The trigger condition states the skill should activate whenever a user needs 'related operations,' which is excessively broad and ambiguous. For a skill with Read, Write, Edit, and Bash tools, vague triggering increases the risk of accidental invocation on inappropriate tasks, leading to unintended file modification, command execution, or external interactions.
The skill is declared as a branch-finishing helper, but the body broadens its scope to generic data processing, external API usage, and command execution. This scope drift is dangerous because it can cause users or orchestration systems to grant powerful file, shell, and network capabilities under a misleading description, increasing the chance of unintended or abusive actions.
The skill advertises convenience and broad capability but does not clearly warn users that it may read/write files, execute shell commands, or access external services. In this context, the omission is dangerous because users may invoke the skill without understanding its high-impact side effects or the permissions it requires.
The core documentation contradicts the manifest by reframing the skill as generic data analysis and workflow orchestration. This mismatch makes the skill more dangerous in context because a branch helper is expected to have a narrow operational scope, while the text encourages a much broader interpretation that could justify over-privileged behavior.
The documentation instructs users to configure API keys, initialize external connections, and rely on networked services without showing why those capabilities are necessary for finishing a development branch. Unjustified credential handling and outbound access expand the attack surface and create opportunities for secret exposure, unintended data exfiltration, or misuse of external services.
The skill presents command execution as a normal operating step even though its stated purpose is branch-oriented assistance, not shell automation. In a skill with Bash access, normalizing command execution without narrow task boundaries can lead to destructive repository changes, arbitrary command abuse, or execution of unsafe user-influenced commands.
No suspicious patterns detected.
