obsidian-backlinks
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
obsidianCLI to perform shell-based operations, such as reading file content and retrieving vault path information (obsidian read,obsidian vault info). These operations are scoped to the local environment and intended for note management. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses local files within the user's Obsidian vault and a configuration file named
.concepts.yamllocated in the workspace. There are no indicators of data being transmitted to external servers or unauthorized access to sensitive system directories. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from Obsidian notes which could theoretically contain malicious instructions.
- Ingestion points: Content is read from user-controlled markdown files via
obsidian read(SKILL.md). - Boundary markers: The skill does not define specific delimiters or warnings to ignore instructions embedded within the notes.
- Capability inventory: The agent can execute shell commands via the
obsidianCLI and write files using thewritetool (SKILL.md). - Sanitization: No explicit sanitization or validation of the ingested note content is mentioned before processing.
Audit Metadata