The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified in the skill's instructions or configuration.
[DATA_EXPOSURE]: The skill does not access sensitive system files (e.g., .ssh, .aws) or contain hardcoded credentials. It manages budget and cost data based solely on user-provided figures.
[REMOTE_CODE_EXECUTION]: There are no commands that download or execute remote scripts or external code. All operations are confined to generating document content using the environment's built-in tools.
[PROMPT_INJECTION]: No instructions were found that attempt to bypass safety guidelines, override system behavior, or extract the agent's internal system prompts.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied project ideas and requirements, which constitutes an ingestion surface for untrusted data.
Ingestion points: External requirement documents or spoken descriptions provided by the user.
Boundary markers: Absent; instructions do not specify delimiters for user input.
Capability inventory: The skill is restricted to document generation (Microsoft Word format).
Sanitization: Not specified; the skill relies on the agent's internal safety filters for processing input.
Risk context: The risk is negligible as the output is a static document intended for human review, and the skill does not possess capabilities like network access or shell execution that could be exploited via malicious input.

proposal-writer