p-blog-writer
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
scripts/skillctx-resolve.pyto manage user-specific configuration data. This script reads and writes to the user's configuration directory at~/.config/skillctx/config.json. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it incorporates external content into the agent's context without sanitization or clear boundary markers.
- Ingestion points: Reads from
{voice_profile_path}and processes untrusted user notes or topics provided during the intake step. - Boundary markers: Absent; instructions do not specify delimiters to separate untrusted content from system instructions.
- Capability inventory: The skill has the ability to write files to
{blog_drafts_dir}and execute the localskillctx-resolve.pyscript. - Sanitization: Absent; there is no validation or filtering of the content retrieved from external files or user input.
Audit Metadata