crawlora
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches data from external, untrusted sources via a third-party API, which creates a surface for indirect prompt injection.
- Ingestion points: Data is retrieved from various public websites via the Crawlora API using the
scripts/crawlora.shutility. - Boundary markers: The instructions do not define specific delimiters or isolation protocols for the agent to follow when processing this external content.
- Capability inventory: The skill uses shell execution to run
scripts/crawlora.shandjq. - Sanitization: No explicit sanitization or validation of the retrieved JSON data is mentioned in the instructions.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local shell script (
scripts/crawlora.sh) and use thejqutility to perform API calls and parse the resulting data.
Audit Metadata