forge-ship
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill directs the agent to ingest content from an external source via directory traversal (
../../../.fullstack-forge/skills/forge-ship/SKILL.md).\n - Ingestion points: SKILL.md (line 14) explicitly directs the agent to read a "canonical playbook" at a relative path outside the skill's root.\n
- Boundary markers: There are no delimiters or explicit instructions to treat the external content as untrusted data.\n
- Capability inventory: The skill enables the agent to navigate the file system and process instructions across directory boundaries.\n
- Sanitization: No validation or sanitization is performed on the target path or the content fetched from it.\n- [PROMPT_INJECTION]: The skill uses imperative, overriding language ("Read the canonical playbook now and follow it exactly") which aims to bypass the agent's current task context in favor of external instructions.
Audit Metadata