pstack-in-your-own-words
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of a single natural language instruction for restating user input and lacks any scripts, binary resources, or configurations that enable tool usage or network access.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied goal and problem statements from a Pstack task. Evidence chain: (1) Ingestion points: the skill instructions involve restating user-provided goals; (2) Boundary markers: no specific delimiters are used to separate user data from instructions; (3) Capability inventory: the skill has no identified dangerous capabilities such as file system writes, network requests, or code execution; (4) Sanitization: none performed. While the attack surface is present, the absence of associated capabilities renders the risk negligible.
Audit Metadata