The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data from external sources such as LinkedIn and Indeed (Steps 3 and 4 in SKILL.md).
Ingestion points: Data returned by nimble search and nimble extract commands in SKILL.md.
Boundary markers: The instructions do not define explicit delimiters or 'ignore' directives to isolate untrusted web content from the agent's core instructions.
Capability inventory: The agent has significant capabilities, including executing shell commands via Bash, file system access via Read and Write, and the ability to spawn sub-agents via the Agent tool.
Sanitization: No sanitization or validation is performed on the content extracted from external candidate profiles before it is presented to the agent.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run commands for environment setup, searching, and profile extraction. It also uses python3 for date manipulation and for updating the user's business profile configuration as described in references/profile-and-onboarding.md.
[EXTERNAL_DOWNLOADS]: The skill documentation provides instructions for installing the @nimbleway/cli package from npm. This package is provided by the skill's author and is required for the skill to perform its intended functions.

talent-sourcing