communication
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's functionality is strictly limited to text analysis and rewriting. It does not request permissions for network access, file system writes, or shell command execution, which prevents typical exploit payloads from causing harm.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process untrusted communication artifacts from users.\n
- Ingestion points: User-provided artifacts (Slack/Teams messages, emails, transcripts, CVs/resumes) processed in the main workflow described in SKILL.md.\n
- Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' instructions to isolate the artifact text from the coaching logic.\n
- Capability inventory: No dangerous capabilities (such as network access, file system access, or subprocess execution) were detected in any of the skill files.\n
- Sanitization: Absent; the skill does not include logic for sanitizing or escaping the content of the ingested artifacts.
Audit Metadata