sya-treat
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from files located in a parent directory (
../satisfy-your-agent/SKILL.mdand../satisfy-your-agent/references/commands.md). This cross-file dependency creates a surface where the agent's behavior can be influenced by content not contained within the skill itself. - Ingestion points: SKILL.md reads external markdown and command reference files.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided.
- Capability inventory: The skill instructs the agent to 'do' actions based on these external files, suggesting the use of tools or commands defined therein.
- Sanitization: There is no validation or filtering of the content read from these external sources.
Audit Metadata