writing-shape
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and processing user-provided markdown files (referred to as the 'pile'). This ingestion of untrusted data creates a surface where malicious instructions embedded in the source material could attempt to influence the agent's output or behavior during the 'shaping' process.\n
- Ingestion points: The agent is instructed to read an input markdown file of raw material in its entirety, as documented in
SKILL.md.\n - Boundary markers: The instructions do not specify the use of boundary markers (like XML tags or delimiters) or explicit 'ignore' directives to isolate the untrusted content from the system instructions.\n
- Capability inventory: The skill facilitates file reads and sequential file writes (appending to an article file). It does not have access to network tools, shell execution, or sensitive environment variables, which significantly limits the potential impact of an injection.\n
- Sanitization: No content sanitization, escaping, or validation of the input file's contents is performed prior to processing.
Audit Metadata