sya-golf
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from relative file paths outside its own directory, creating an attack surface where malicious instructions in those files could influence agent behavior.
- Ingestion points: Reads instructions and activity definitions from
../satisfy-your-agent/SKILL.mdand../satisfy-your-agent/references/activities.md(SKILL.md). - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" markers for the ingested content to prevent the agent from obeying instructions found within the data.
- Capability inventory: The skill is intended to perform "code-golf," which involves generating and executing toy code snippets, providing a path for potential command execution if the input is poisoned.
- Sanitization: There is no explicit sanitization, validation, or filtering of the ingested file content before it is interpolated into the agent's context.
Audit Metadata