The Agent Skills Directory

[SAFE]: The skill consists of markdown instructions and references to local templates. It contains no executable scripts, shell commands, or dynamic code execution patterns.
[SAFE]: No external network calls, data exfiltration patterns, or credential handling were identified. The author contact information provided is for attribution purposes and does not represent a malicious exfiltration point.
[PROMPT_INJECTION]: The skill defines a workflow for the agent to ingest and analyze potentially untrusted external documents (e.g., tender documents, architecture evidence). This creates an attack surface for indirect prompt injection if those documents contain adversarial instructions. However, the risk is minimal as the agent's primary function is drafting text within a controlled workspace without network or system modification capabilities.
Ingestion points: Tender, discovery, architecture, commercial, security, and operating evidence files.
Boundary markers: No specific delimiters or instructions for the agent to ignore instructions embedded in the external data were identified in the workflow.
Capability inventory: The skill involves reading workspace files and drafting proposal artifacts; it lacks capabilities for network access, subprocess execution, or writing to production systems.
Sanitization: No evidence of content filtering or validation of the ingested external data was found.

saas-procurement-and-security-questionnaire