proposal-writing

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (ls) to discover installed companion skills in specific directories such as ~/.claude/skills/, ~/.agent/skills/, and .agent/skills/. This is performed during the 'Companion check' to recommend additional tools from the same vendor.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted external data (RFPs and project requirements) without employing boundary markers or sanitization logic.
  • Ingestion points: External text provided by users for RFP responses, Statement of Work (SOW) drafting, and requirement shredding as defined in the 'Respond to an RFP systematically' workflow.
  • Boundary markers: No delimiters or instructions to ignore embedded directives are present in the processing logic.
  • Capability inventory: The agent is authorized to execute shell discovery commands (ls) and perform file system operations to draft proposals.
  • Sanitization: The skill does not implement validation or escaping for content extracted from external documents before it is interpolated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 01:04 PM
Security Audit — agent-trust-hub — proposal-writing