post-writer
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses authoritative directives in the 'CRITICAL: Auto-start on load' section, instructing the agent to 'Do not summarise the skill' and 'Do not explain what it does'. These instructions attempt to override the agent's standard interaction behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, which creates a potential surface for indirect prompt injection.
- Ingestion points: The skill reads user-pasted 'context dumps', 'notes', and 'transcripts' during the input gathering phase.
- Boundary markers: There are no explicit delimiters or specific instructions to the agent to ignore any hidden commands within the ingested text before it is processed.
- Capability inventory: The skill has the ability to write files to the local project environment ('save the final post as a markdown file').
- Sanitization: No sanitization or validation of the ingested user content is performed before it is interpolated into the generation instructions.
Audit Metadata