writing-fragments
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and append to a markdown file specified by the user. Because it re-reads the file from disk before every write to preserve changes, it could ingest malicious instructions if the file contains untrusted content.
- Ingestion points: The skill reads the content of a markdown file from a user-provided path (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the logic.
- Capability inventory: The agent has the capability to write, append, and edit files on the local filesystem (SKILL.md).
- Sanitization: There is no evidence of sanitization or filtering applied to the content read from the file before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill requires the agent to interact with the local filesystem to create, read, and append to files. While this is the primary purpose of the skill, it allows the agent to access any file path the user specifies, which could include sensitive system or configuration files if the user is misled or if the agent is compromised via indirect injection.
Audit Metadata