conversation-context-import
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands to inspect the local git environment.
- Evidence: Executes
git branch --show-currentandgit worktree listto retrieve branch names and directory paths. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection by ingesting untrusted data from external sources.
- Ingestion points: The skill reads the full content of markdown files in the
.dev/contexts/directory and text from GitHub Pull Request comments (SKILL.md, Step 2 and 4). - Boundary markers: There are no instructions to use delimiters or specific system prompts to isolate the imported context from the agent's core instructions.
- Capability inventory: The agent reads and incorporates the retrieved text into its active conversation context, which influences subsequent actions.
- Sanitization: The skill does not perform any validation or sanitization on the content of the imported context files or PR comments beyond branch name sanitization for file paths.
Audit Metadata