shieldcn-badges
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to inspect existing project files, such as README.md and package metadata, to determine which badges and visual elements to add. This processing of untrusted external data creates a surface for indirect prompt injection.
- Ingestion points: In
SKILL.md, the agent is directed to "Inspect the existing README and package metadata before editing." - Boundary markers: The skill lacks explicit instructions or delimiters to tell the agent to ignore potentially malicious instructions embedded within the files it analyzes.
- Capability inventory: The skill's instructions primarily involve generating Markdown and HTML snippets. It does not request the agent to execute shell commands, access sensitive system files, or perform network requests directly (network activity is offloaded to the external rendering service).
- Sanitization: There are no requirements for the agent to sanitize or validate the content ingested from the project files before incorporating it into its reasoning or output.
Audit Metadata