compress-prompt
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process arbitrary user-provided text ('Prompt P') for compression, creating a surface for indirect prompt injection where embedded instructions could attempt to influence the agent's behavior.
- Ingestion points: Untrusted text enters the agent context through the prompt provided by the user for compression as described in SKILL.md.
- Boundary markers: Absent; the instructions do not define specific delimiters (such as xml tags or triple backticks) or provide directives to ignore instructions within the input variable P.
- Capability inventory: None; the skill does not utilize any tools, perform network requests, or interact with the file system.
- Sanitization: Absent; the input text is not filtered or validated before being processed by the language model.
Audit Metadata