my
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a 'scratchpad' feature (
my(action="set")) that allows the agent to store and retrieve arbitrary session-specific data. This creates a surface for indirect prompt injection, where data provided by a user in one turn could contain instructions that influence the agent's behavior when retrieved in a subsequent turn.\n - Ingestion points: The
setaction of themytool allows storing values in the session scratchpad (documented in SKILL.md and references/examples.md).\n - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within retrieved scratchpad values.\n
- Capability inventory: The skill provides access to runtime configuration and metadata but does not include high-risk capabilities like network access, file system modifications, or arbitrary command execution in the scripts analyzed.\n
- Sanitization: There is no explicit sanitization or validation logic described for the content stored in or retrieved from the scratchpad.
Audit Metadata