The Agent Skills Directory

[PROMPT_INJECTION]: No direct prompt injection or system prompt extraction attempts were found in the skill instructions.
[NO_CODE]: The skill provides documentation and platform configuration but lacks the actual script logic (referenced .js files) for analysis.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data.
Ingestion points: Untrusted process descriptions and BPMN XML content are ingested via usage prompts defined in SKILL.md.
Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or to ignore embedded instructions within the ingested XML or text.
Capability inventory: The skill is granted Bash, Write, and Read permissions in SKILL.md, which could be abused if an indirect injection is successful.
Sanitization: There is no evidence of input validation or sanitization for the process descriptions provided by users.

bpmn-generator