post-formatter
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses imperative instructions to override the agent's standard conversational flow, specifically using the marker 'CRITICAL: Auto-start on load' and directives like 'Do not summarise' and 'Start input gathering immediately.' While functional for the skill's purpose, these patterns attempt to bypass default agent behavior.
- [PROMPT_INJECTION]: The skill exhibits a vulnerability to indirect prompt injection.
- Ingestion points: The skill ingests untrusted data through the 'Topic' and 'context dump' fields in the
AskUserQuestiontool, as well as a follow-up question for facts and tone notes. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the user input as data only or to ignore any embedded instructions within that content.
- Capability inventory: The skill has the capability to generate and output structured text based on these inputs.
- Sanitization: There is no evidence of sanitization, escaping, or validation of the user-provided content before it is processed by the agent.
Audit Metadata