journalist-media-research
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill incorporates robust security controls. The helper script
scripts/crawlora.shmanages API keys securely using temporary files with restricted permissions and avoids exposing sensitive data in command-line arguments. It also enforces a strict whitelist of allowed API paths and HTTP methods. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, which is necessary for its core functionality of media research.
- Ingestion points: The skill retrieves external content via the
/web/scrapeand/datasets/journalists/searchendpoints using thecrawlora.shscript. - Boundary markers: No explicit delimiters are specified in the instructions to separate external content from internal prompts.
- Capability inventory: The skill's capabilities are confined to authorized API calls to the vendor's platform. It lacks dangerous capabilities such as local file writing or arbitrary command execution.
- Sanitization: The script includes defensive checks, such as regex-based path validation and the rejection of the '@' character in query parameters, to prevent unauthorized file access via curl.
Audit Metadata