The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user/agent to install a third-party command-line interface tool using npm install -g @curviate/cli. The provider of this package is not recognized as a trusted organization or well-known service, which means the agent is executing unverified code from an external repository.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection by processing data retrieved from external LinkedIn profiles and resumes.
Ingestion points: Untrusted data enters the agent context through the curviate job applicant get and curviate job applicant resume commands described in SKILL.md.
Boundary markers: The skill lacks explicit delimiters or instructions to the agent to disregard instructions that might be embedded within applicant profile data or resume content.
Capability inventory: The agent has the capability to perform various job management tasks via the curviate CLI, including creating, updating, and publishing postings.
Sanitization: There is no mention of sanitization or validation of the external content before it is interpolated into the agent's workflow.
[COMMAND_EXECUTION]: The skill's primary functionality is built around the execution of shell commands via the curviate CLI, granting the agent the ability to interact with the host system and remote LinkedIn services.

curviate-jobs