inkos-continuation-writing
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze 'imported text', 'compressed source packages', and 'retrieved passages' to reconstruct established facts and character knowledge. This represents a data ingestion surface where instructions hidden within the source stories could potentially influence the agent's behavior.
- Ingestion points: The skill processes user-provided story text and retrieved canon data as described in
SKILL.md. - Boundary markers: There are no explicit instructions for the agent to treat the imported content as untrusted or to ignore embedded commands.
- Capability inventory: The primary capability is text generation for creative writing. No dangerous system commands or network operations are present in the skill.
- Sanitization: The skill does not define methods for sanitizing or filtering instructions that might be present in the imported text.
Audit Metadata