release
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input through the $ARGUMENTS variable and passes it directly into the agent context as a task.
- Ingestion points: The $ARGUMENTS variable in SKILL.md.
- Boundary markers: No delimiters (such as XML tags or Markdown blocks) or specific instructions are used to isolate the user input from the skill's operational logic.
- Capability inventory: The skill triggers the version-bump and childhood skills to automate coding sessions and release processes.
- Sanitization: No input validation or escaping mechanisms are present to prevent malicious instructions within the user arguments from influencing the agent's behavior.
Audit Metadata