The Agent Skills Directory

Metadata Discrepancy: The author specified in the skill's metadata ("Microsoft Manufacturing Skills") differs from the holder named in the license file ("Sravani Seethi"). While likely a documentation oversight, this inconsistency is a consideration when verifying the skill's provenance.
Indirect Prompt Injection Surface: The skill processes external data via the impact.json file. This represents an attack surface where untrusted content could potentially influence the agent.
Ingestion points: Data is ingested from impact.json (referenced in SKILL.md).
Boundary markers: No explicit delimiters or instructions to ignore embedded content are present in the provided instructions.
Capability inventory: The skill does not possess capabilities for network exfiltration, arbitrary file writing, or command execution, which limits the potential impact of an injection.
Sanitization: There is no evidence of input sanitization for the content processed from impact.json.

standards-check