ats-job-boards-research
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a bash helper script (scripts/crawlora.sh) to handle interactions with the Crawlora API. The script is securely constructed using 'set -euo pipefail' and proper variable quoting to prevent command injection vulnerabilities.
- [DATA_EXFILTRATION]: The skill performs network requests to api.crawlora.net, which is the official API endpoint for the skill's authoring organization. It uses an API key supplied by the user via an environment variable, which is a standard and secure practice for secret management.
- [PROMPT_INJECTION]: The skill processes job descriptions and metadata retrieved from external Applicant Tracking Systems. This ingestion of untrusted data constitutes a surface for indirect prompt injection.
- Ingestion points: External job board content is fetched via scripts/crawlora.sh from api.crawlora.net.
- Boundary markers: No specific delimiters are used in the prompt instructions to isolate external data from system instructions.
- Capability inventory: The skill can execute network requests using the provided bash utility.
- Sanitization: No explicit filtering or sanitization is performed on the job descriptions before they are returned to the agent's context.
Audit Metadata