social-context
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by design. It reads existing context files to determine which interview questions to ask or update.\n
- Ingestion points:
social-context.mdat the project root and.agents/social-context.md(SKILL.md).\n - Boundary markers: Absent. The agent is instructed to read the file content directly without delimiters or instructions to ignore embedded commands.\n
- Capability inventory: The skill has the capability to write to and update
social-context.mdon the local filesystem (SKILL.md).\n - Sanitization: Absent. There is no logic provided to sanitize or validate the content retrieved from the markdown files before it is processed by the agent.\n- [NO_CODE]: The skill consists entirely of markdown instructions and configuration files. It does not include any executable scripts (e.g., Python, JavaScript) or binary files, which significantly reduces the potential attack surface for remote code execution or persistence.
Audit Metadata