writing-stickiness
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided draft messages to apply writing improvements, which creates a surface where the agent might be influenced by instructions embedded within the untrusted text.
- Ingestion points: Draft text or messages provided by the user for enhancement in SKILL.md.
- Boundary markers: Absent; the instructions do not specify delimiters for the input draft or include directives for the agent to ignore instructions embedded in the user text.
- Capability inventory: The workflow involves writing and reading local analysis files (writer-stickiness-analysis.md) but does not include network operations or system-level execution tools.
- Sanitization: No sanitization, filtering, or validation of the input draft content is performed before processing.
Audit Metadata