muse-wiki
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill compiles project memories into a documentation wiki, which creates a vulnerability surface where instructions embedded in those memories could influence the agent when it later reads the generated pages.
- Ingestion points: The
memory_wiki_compiletool processes data from the project's confirmed memory store as described inSKILL.md. - Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between generated documentation and potential instructions within that data.
- Capability inventory: The skill performs file system writes to the
.memory/wiki/directory and reads synthesized content via search and get tools. - Sanitization: No sanitization or escaping mechanisms are described for the data being compiled into the markdown pages.
- [COMMAND_EXECUTION]: The skill includes documentation for local CLI commands (
memory wiki,memory entities) to compile and interact with the knowledge graph.
Audit Metadata