project-context
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the user's conversation history to generate summarized project instructions. This creates a surface for indirect prompt injection if malicious instructions are embedded in the source conversation and subsequently included in the generated output.
- Ingestion points: The agent gathers content from the active conversation to summarize (SKILL.md).
- Boundary markers: Absent; the instructions do not specify delimiters to separate untrusted source content from the summarization logic.
- Capability inventory: The skill's primary capability is text summarization and formatting within Markdown blocks; it does not perform subprocess execution, file writes, or network operations.
- Sanitization: Absent; the instructions do not include steps to filter or escape potentially malicious input within the conversation data.
Audit Metadata