The Agent Skills Directory

[SAFE]: The skill acts as a documentation and style guide for technical publishing. No malicious patterns such as code execution, data exfiltration, or obfuscation were identified.
[INDIRECT_PROMPT_INJECTION]: The skill processes application metadata and documentation, presenting a surface for indirect prompt injection.
Ingestion points: The skill reads robium-app.yaml, docs/case-study.md, and README files from the application repository.
Boundary markers: No specific delimiters or warnings for embedded instructions are present.
Capability inventory: The skill's capabilities are limited to generating editorial content; it lacks access to tools for command execution, network requests, or file-system modification.
Sanitization: No sanitization or filtering of ingested data is documented.
Verdict rationale: Given the lack of dangerous capabilities, the injection surface does not pose a security threat.

app-publishing