aim
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data sources such as files, repositories, pastes, and chat history. This creates a surface for indirect prompt injection where instructions hidden in the processed data could influence the agent's behavior.
- Ingestion points: SKILL.md explicitly mentions reading 'files, a repo, a paste, a chat scrollback'.
- Boundary markers: The skill lacks instructions for the agent to use delimiters or specific framing to distinguish data from instructions.
- Capability inventory: The skill uses the agent's default tools to read data and formulate proposals; no dangerous shell or network tools are added.
- Sanitization: There are no instructions for the agent to sanitize, escape, or ignore instructions embedded within the provided data.
- [NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata. It does not include any scripts, executable binaries, or references to external package managers, which significantly reduces the attack surface for code-based exploits.
Audit Metadata