The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data in the text field, which constitutes an attack surface for instructions embedded within the processed content.
Ingestion points: The text input parameter defined in SKILL.md and manifest.json.
Boundary markers: Absent; there are no specific delimiters or instructions for the agent to ignore instructions embedded within the input text.
Capability inventory: The skill is restricted to the Read tool (manifest.json). It lacks capabilities for file modification, network communication, or system command execution.
Sanitization: Absent; the skill does not specify any pre-processing or filtering of the input text.
[EXTERNAL_DOWNLOADS]: The skill references an external site for informational and attestation purposes.
Evidence: Mentions starlightintelligence.org/protocol in the metadata and attestation fields as the source of the 'Starlight Intelligence Protocol'. This is documented as a neutral reference to vendor-related documentation.

starlight-voice