resume-builder
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data that could potentially contain hidden instructions designed to influence the LLM's behavior.
- Ingestion points: Reads external LinkedIn PDF exports and job descriptions via the
braggerCLI tool. - Boundary markers: Absent. The instructions do not define specific delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill has the ability to read from and write to a local knowledge base and the filesystem (
outputs/directory) via thebraggertool. - Sanitization: Absent. There is no evidence of input validation or escaping for the data ingested from PDFs or JDs.
- [COMMAND_EXECUTION]: The skill utilizes a custom CLI tool
braggerto manage candidate data. This is an integrated part of the skill's functionality and operates on local data. - [METADATA_POISONING]: Metadata fields such as name and description are descriptive and match the skill's actual behavior without signs of deception.
Audit Metadata