CVE-2026-39909: Llama Interactive Specials Token Injection
Tokenizing user input with `parse_special` enabled (such as `params.interactive_specials`) allows user input to parse into control tokens, enabling prompt injection and control hijacking.
Provally CuratedPublic repositoryMediumMedium confidenceVerifiedApache-2.0
C++
C++greprules fetch cve-2026-39909-llama-interactive-specials-token-injection --engine opengrepDescription
Tokenizing user input with `parse_special` enabled (such as `params.interactive_specials`) allows user input to parse into control tokens, enabling prompt injection and control hijacking.
Community feedback
0 rule-level signals from signed-in users.
- Useful reports
- 0
- Context false positives
- 0
- Metadata suggestions
- 0
Contextual precision
Aggregated from approved scan feedback. False-positive reports describe observed scan contexts, not a global rule verdict.
- Findings observed
- 0
- Projects
- 0
- Reporters
- 0
Precision details are collecting more signed-in reports before verdict counts or ratios are emphasized.
Finding verdicts0
No approved finding verdicts yet.
Scan diagnostics0
No scan diagnostics reported yet.