track17
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches parcel tracking information and carrier metadata from official 17TRACK domains (api.17track.net and res.17track.net). These requests are necessary for the skill's primary functionality.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests tracking descriptions and event data from the 17TRACK API and through a local webhook server.\n
- Ingestion points: Data is received via the
urllibmodule inscripts/track17.pyand through a built-inhttp.serverfor webhooks.\n - Boundary markers: None specific are implemented to delimit parcel description strings from the agent's instructions.\n
- Capability inventory: The script
scripts/track17.pyperforms file writes to a local SQLite database and network POST requests to the 17TRACK API.\n - Sanitization: The skill parses incoming data as JSON but does not perform specific sanitization or filtering to detect or remove potential prompt injection patterns within tracking descriptions.
Audit Metadata