fast-ship
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
- [DATA_EXFILTRATION]: The skill manages a configuration file (~/.config/fast-ship/config.yaml) that contains a sensitive API key and performs network requests to a user-provided Base URL. While this is the primary functionality of the skill, the combination of sensitive file access and network capabilities is noted. The skill implements mitigation strategies by using a script to handle authentication, preventing the API key from appearing in command-line arguments or environment variables.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external REST API and has capabilities to write data back, creating a vulnerability surface.\n
- Ingestion points: Data retrieved from GET requests to /api/projects/{id}/issues, /api/issues/{iid}, and associated collaborative endpoints (consensus, summary).\n
- Boundary markers: Absent. The skill instructions do not provide delimiters or warnings to the agent to ignore instructions embedded in the API data.\n
- Capability inventory: The skill can perform state-changing POST, PUT, and DELETE operations via the fast-ship-api.mjs script.\n
- Sanitization: Absent. The skill does not define any sanitization or filtering logic for data processed from the external API.\n- [EXTERNAL_DOWNLOADS]: The skill includes instructions to download and install itself from a GitHub repository (https://github.com/gitbobobo/fast_ship) using npx. This is documented as the standard installation procedure and originates from the skill author's repository.
Audit Metadata