skills/gharib89/skills/cloud-ship/Gen Agent Trust Hub

cloud-ship

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command using sed to extract the version number from the skill's own SKILL.md file for reporting purposes. This is a benign use of system utilities for self-metadata retrieval.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and relay output from the ship skill verbatim, which introduces a potential surface for indirect prompt injection if the source skill's output is compromised. 1. Ingestion points: The agent reads the 'step-5 result' and 'merge summary' produced by the ship skill. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the relayed content are provided. 3. Capability inventory: The skill invokes the ship tool and performs text processing with sed. 4. Sanitization: Output is relayed verbatim without sanitization or validation steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 03:46 PM