tcm-constitution-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted health and activity data from various local storage files, which could potentially contain instructions aimed at influencing the agent's behavior.
- Ingestion points: Data enters the agent's context through files such as
data-example/tcm-constitution-tracker.json,data-example/nutrition-tracker.json,data-example/fitness-tracker.json,data-example/sleep-tracker.json, and daily records indata-example/tcm-constitution-logs/(specified inreferences/detailed-guide.md). - Boundary markers: The instructions rely on markdown headers for structure but lack explicit delimiters or specific warnings to ignore instructions embedded within the ingested JSON content.
- Capability inventory: The skill is configured to use the
Read,Grep,Glob, andWritetools as defined in theSKILL.mdfrontmatter. - Sanitization: There is no documented logic for input validation, sanitization, or escaping of the external JSON data before it is interpolated into the agent's reasoning process.
Audit Metadata