openjobs-people-match
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to manage configuration and perform network requests.
- Evidence: Uses
mkdir -p ~/.config/miraandechoto initialize and store API keys in the local file system. - Evidence: Uses
catandexportto retrieve credentials and set environment variables. - Evidence: Uses
curlto interact with the vendor's REST API and version endpoints. - [EXTERNAL_DOWNLOADS]: The skill implements a version check and update mechanism using external resources.
- Evidence: Fetches version metadata from
https://mira-api.openjobs-ai.com/v1/version. - Evidence: Provides instructions to download and replace the skill file from the vendor's official repository at
https://raw.githubusercontent.com/OpenJobsAI/openjobs-openclaw-skills/main/openjobs-people-match/SKILL.md. - [PROMPT_INJECTION]: The skill presents an indirect injection surface by processing external candidate data.
- Ingestion points: Candidate resumes and LinkedIn profile URLs are passed directly to the OpenJobs AI API.
- Boundary markers: No explicit boundary markers or isolation instructions are present in the CV processing logic.
- Capability inventory: The skill has the capability to execute network requests via
curland read/write local configuration files. - Sanitization: No explicit sanitization or filtering of candidate-provided text is performed before transmission.
Audit Metadata