ship-digest
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external GitHub repositories, which constitutes an indirect prompt injection surface.
- Ingestion points: README content and commit messages are retrieved via
gh apiinSKILL.md(Step 2). - Boundary markers: The prompt instructions lack delimiters or specific directives to the model to ignore potential instructions embedded within the repository content.
- Capability inventory: The skill reads file structures, decodes content, and is intended to trigger other social media posting skills.
- Sanitization: No sanitization or content validation is performed on the data fetched from GitHub before it is processed by the LLM.
- [COMMAND_EXECUTION]: The skill uses standard GitHub CLI (
gh api) and system utility (base64) commands to manage its workflow. These operations are consistent with the skill's primary purpose and do not involve unauthorized privilege escalation or persistence mechanisms.
Audit Metadata