alterlab-pra-pitch-builder

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows a standard professional workflow for its stated purpose. It defines a persona, clear objectives, and structured outputs without attempting to bypass safety guidelines or access sensitive system resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external information, which is a standard surface for indirect prompt injection.
  • Ingestion points: The skill explicitly instructs the agent to 'Search the web for industry award winners, case study examples...' and 'Read existing project files for context — client briefs, RFP documents...' (SKILL.md).
  • Boundary markers: Absent. There are no explicit instructions to the agent to disregard potential instructions embedded within the files or web content it reads.
  • Capability inventory: The skill has the capability to perform web searches and write output to local markdown files (e.g., {project}-pitch-deck.md).
  • Sanitization: Absent. The skill does not define specific validation or escaping logic for the content it retrieves before incorporating it into the final deliverables.
  • [DATA_EXPOSURE]: The skill accesses local project files such as briefs and RFP documents. This behavior is documented and necessary for the skill's primary function of building context-aware presentations. It does not attempt to access credentials, SSH keys, or environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 11:44 PM
Security Audit — agent-trust-hub — alterlab-pra-pitch-builder