bid-cover-formatter
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided document text which serves as an ingestion point for untrusted data. An attacker could potentially embed instructions within tender document fields (e.g., project names or company titles). However, the skill lacks any capabilities (such as network access or file system modification) to execute malicious actions beyond generating formatted text.
- Ingestion points: User-supplied Markdown content processed during the 'Identify' and 'Parse' steps.
- Boundary markers: None present in the instructions to delimit or ignore instructions within the input data.
- Capability inventory: The skill has no active tools or permissions for file writing, network requests, or command execution.
- Sanitization: The skill extracts raw strings from input and interpolates them directly into the output template without filtering.
Audit Metadata