cricket-player-team-comparison
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data fetched from the Cricinfo API, which constitutes an attack surface for instructions embedded in sports data.
- Ingestion points: Data is retrieved via
scripts/crawlora.shfrom theapi.crawlora.netservice (e.g., player names, match scorecards, and record tables). - Boundary markers: The instructions in
SKILL.mddo not define delimiters or specific warnings to the agent to ignore potentially malicious instructions found within the cricket statistics data. - Capability inventory: The skill includes
scripts/crawlora.sh, which executes shell commands (curl) and has access to environment variables (CRAWLORA_API_KEY). - Sanitization: While the
crawlora.shscript provides robust validation for API keys and request paths to prevent local command injection, it does not sanitize or filter the content of the data returned by the API before it is ingested by the agent.
Audit Metadata